In [1]:
%run ADL_sea.ipynb
Number of input: 3 Number of output: 2 Number of batch: 100 All labeled
100% (100 of 100) |######################| Elapsed Time: 0:02:38 ETA: 00:00:00
=== Performance result === Accuracy: 91.77878787878788 (+/-) 7.774645046654492 Testing Loss: 0.2475769944075081 (+/-) 0.17538645165333314 Precision: 0.9180847507481505 Recall: 0.9177878787878788 F1 score: 0.9169805927240723 Testing Time: 0.004532293839888139 (+/-) 0.006663265097464228 Training Time: 1.5917126915671609 (+/-) 0.14680636875031983 === Average network evolution === Total hidden node: 10.525252525252526 (+/-) 4.409226859880036 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=3, out_features=18, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=18, out_features=2, bias=True) ) No. of inputs : 3 No. of nodes : 18 No. of parameters : 110 Voting weight: [1.0]
100% (100 of 100) |######################| Elapsed Time: 0:02:47 ETA: 00:00:00
=== Performance result === Accuracy: 91.63737373737374 (+/-) 7.9348685280406555 Testing Loss: 0.248694378581613 (+/-) 0.17716825433551067 Precision: 0.9166299192863216 Recall: 0.9163737373737374 F1 score: 0.9155568032410182 Testing Time: 0.004933330747816298 (+/-) 0.007703368873455288 Training Time: 1.6848876957941537 (+/-) 0.05137850635048642 === Average network evolution === Total hidden node: 7.828282828282828 (+/-) 4.917584206199083 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=3, out_features=15, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=15, out_features=2, bias=True) ) No. of inputs : 3 No. of nodes : 15 No. of parameters : 92 Voting weight: [1.0]
100% (100 of 100) |######################| Elapsed Time: 0:02:45 ETA: 00:00:00
=== Performance result === Accuracy: 91.60000000000001 (+/-) 7.599774052994318 Testing Loss: 0.2515264848115468 (+/-) 0.17756957551505967 Precision: 0.9168156406672259 Recall: 0.916 F1 score: 0.9149588010903454 Testing Time: 0.005166641389480745 (+/-) 0.007896823959998392 Training Time: 1.6596386336316966 (+/-) 0.03279892095374525 === Average network evolution === Total hidden node: 11.323232323232324 (+/-) 4.8675970111747775 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=3, out_features=20, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=20, out_features=2, bias=True) ) No. of inputs : 3 No. of nodes : 20 No. of parameters : 122 Voting weight: [1.0]
100% (100 of 100) |######################| Elapsed Time: 0:02:43 ETA: 00:00:00
=== Performance result === Accuracy: 92.51313131313131 (+/-) 6.005917056522474 Testing Loss: 0.24561232618159717 (+/-) 0.16810259909722203 Precision: 0.9251274808780803 Recall: 0.9251313131313131 F1 score: 0.9246032873653983 Testing Time: 0.005292723877261383 (+/-) 0.007490605758028644 Training Time: 1.6460770284286652 (+/-) 0.024563431714747435 === Average network evolution === Total hidden node: 10.767676767676768 (+/-) 4.199154034158735 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=3, out_features=18, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=18, out_features=2, bias=True) ) No. of inputs : 3 No. of nodes : 18 No. of parameters : 110 Voting weight: [1.0]
100% (100 of 100) |######################| Elapsed Time: 0:02:30 ETA: 00:00:00
=== Performance result === Accuracy: 92.28787878787878 (+/-) 6.410885199082313 Testing Loss: 0.24687982346824924 (+/-) 0.17060163623546878 Precision: 0.9229782102311964 Recall: 0.9228787878787879 F1 score: 0.9222569323384725 Testing Time: 0.005219413776590367 (+/-) 0.007124591540430939 Training Time: 1.5094771722350457 (+/-) 0.18872308541102747 === Average network evolution === Total hidden node: 14.505050505050505 (+/-) 4.628357339717398 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=3, out_features=22, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=22, out_features=2, bias=True) ) No. of inputs : 3 No. of nodes : 22 No. of parameters : 134 Voting weight: [1.0]
Mean Accuracy: 92.18530612244899 Std Accuracy: 6.840025391419877 Hidden Node mean 11.046938775510204 Hidden Node std: 5.072116735636615 Hidden Layer mean: 1.0 Hidden Layer std: 0.0 50% labeled
100% (100 of 100) |######################| Elapsed Time: 0:01:03 ETA: 00:00:00
=== Performance result === Accuracy: 90.789898989899 (+/-) 8.582357931627218 Testing Loss: 0.27071312513917384 (+/-) 0.17561097302458126 Precision: 0.9088370624415407 Recall: 0.9078989898989899 F1 score: 0.9066235507421124 Testing Time: 0.004466723914098258 (+/-) 0.006532980041181871 Training Time: 0.6369590277623649 (+/-) 0.015738429264258714 === Average network evolution === Total hidden node: 12.282828282828282 (+/-) 3.954387421536252 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=3, out_features=20, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=20, out_features=2, bias=True) ) No. of inputs : 3 No. of nodes : 20 No. of parameters : 122 Voting weight: [1.0]
100% (100 of 100) |######################| Elapsed Time: 0:01:03 ETA: 00:00:00
=== Performance result === Accuracy: 90.72323232323232 (+/-) 8.656903921823464 Testing Loss: 0.27458650581162386 (+/-) 0.1740398787779756 Precision: 0.9085636748176429 Recall: 0.9072323232323233 F1 score: 0.9058076866681034 Testing Time: 0.003949100320989435 (+/-) 0.0054398273542768695 Training Time: 0.6349737909105089 (+/-) 0.03386464524745355 === Average network evolution === Total hidden node: 11.777777777777779 (+/-) 3.9557030956481447 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=3, out_features=19, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=19, out_features=2, bias=True) ) No. of inputs : 3 No. of nodes : 19 No. of parameters : 116 Voting weight: [1.0]
100% (100 of 100) |######################| Elapsed Time: 0:01:02 ETA: 00:00:00
=== Performance result === Accuracy: 90.5838383838384 (+/-) 8.925784995845577 Testing Loss: 0.2734414122697681 (+/-) 0.17615246614542596 Precision: 0.9083339242387399 Recall: 0.9058383838383839 F1 score: 0.9040395948406204 Testing Time: 0.0038553488374960545 (+/-) 0.005011258493050731 Training Time: 0.6251076447843301 (+/-) 0.013943595998541655 === Average network evolution === Total hidden node: 9.545454545454545 (+/-) 3.939627032730991 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=3, out_features=16, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=16, out_features=2, bias=True) ) No. of inputs : 3 No. of nodes : 16 No. of parameters : 98 Voting weight: [1.0]
100% (100 of 100) |######################| Elapsed Time: 0:01:02 ETA: 00:00:00
=== Performance result === Accuracy: 89.12828282828282 (+/-) 10.965464983476375 Testing Loss: 0.28966213378942374 (+/-) 0.1976872619703256 Precision: 0.8954560942810239 Recall: 0.8912828282828282 F1 score: 0.8885168794829359 Testing Time: 0.0036543017686015426 (+/-) 0.004977736961850179 Training Time: 0.6244075201978587 (+/-) 0.018499661143103075 === Average network evolution === Total hidden node: 5.484848484848484 (+/-) 3.804207230660659 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=3, out_features=12, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=12, out_features=2, bias=True) ) No. of inputs : 3 No. of nodes : 12 No. of parameters : 74 Voting weight: [1.0]
100% (100 of 100) |######################| Elapsed Time: 0:01:02 ETA: 00:00:00
=== Performance result === Accuracy: 91.03333333333335 (+/-) 8.046430917186234 Testing Loss: 0.27042536900350544 (+/-) 0.17240731220981606 Precision: 0.9118056129039311 Recall: 0.9103333333333333 F1 score: 0.9089480132814006 Testing Time: 0.004172349216962102 (+/-) 0.006375912688472921 Training Time: 0.6282619876090927 (+/-) 0.01449281374351998 === Average network evolution === Total hidden node: 8.777777777777779 (+/-) 3.909469352390929 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=3, out_features=16, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=16, out_features=2, bias=True) ) No. of inputs : 3 No. of nodes : 16 No. of parameters : 98 Voting weight: [1.0]
Mean Accuracy: 90.71448979591837 Std Accuracy: 8.773965096534292 Hidden Node mean 9.614285714285714 Hidden Node std: 4.609240939766148 Hidden Layer mean: 1.0 Hidden Layer std: 0.0 25% labeled
100% (100 of 100) |######################| Elapsed Time: 0:00:31 ETA: 00:00:00
=== Performance result === Accuracy: 85.8787878787879 (+/-) 13.171466503161046 Testing Loss: 0.3355905680042325 (+/-) 0.20088427162846714 Precision: 0.8686284666298859 Recall: 0.8587878787878788 F1 score: 0.8526720595334817 Testing Time: 0.004018894349685823 (+/-) 0.007422354144938157 Training Time: 0.3165863668075716 (+/-) 0.011347629563175804 === Average network evolution === Total hidden node: 3.595959595959596 (+/-) 2.173853776313337 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=3, out_features=8, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=8, out_features=2, bias=True) ) No. of inputs : 3 No. of nodes : 8 No. of parameters : 50 Voting weight: [1.0]
100% (100 of 100) |######################| Elapsed Time: 0:00:31 ETA: 00:00:00
=== Performance result === Accuracy: 88.98484848484847 (+/-) 10.402693548204294 Testing Loss: 0.30224385067369 (+/-) 0.1865478362791381 Precision: 0.8939479485291837 Recall: 0.8898484848484849 F1 score: 0.8870408605837202 Testing Time: 0.004059622986148102 (+/-) 0.006205225922172628 Training Time: 0.3140897269200797 (+/-) 0.009588336907420426 === Average network evolution === Total hidden node: 7.474747474747475 (+/-) 3.0890599869373956 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=3, out_features=13, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=13, out_features=2, bias=True) ) No. of inputs : 3 No. of nodes : 13 No. of parameters : 80 Voting weight: [1.0]
100% (100 of 100) |######################| Elapsed Time: 0:00:31 ETA: 00:00:00
=== Performance result === Accuracy: 88.6030303030303 (+/-) 10.67551200054729 Testing Loss: 0.31178097810709116 (+/-) 0.18547889571966275 Precision: 0.8907633510458334 Recall: 0.8860303030303031 F1 score: 0.8828870303009299 Testing Time: 0.0041606594817806975 (+/-) 0.006289658859874122 Training Time: 0.3164662688669532 (+/-) 0.010643389254065955 === Average network evolution === Total hidden node: 9.393939393939394 (+/-) 2.7370196200187005 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=3, out_features=15, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=15, out_features=2, bias=True) ) No. of inputs : 3 No. of nodes : 15 No. of parameters : 92 Voting weight: [1.0]
100% (100 of 100) |######################| Elapsed Time: 0:00:31 ETA: 00:00:00
=== Performance result === Accuracy: 89.87979797979798 (+/-) 8.677545384414982 Testing Loss: 0.2955809903114733 (+/-) 0.16807242257865118 Precision: 0.9017287144777161 Recall: 0.8987979797979798 F1 score: 0.896649173317882 Testing Time: 0.0038671806605175287 (+/-) 0.005369903093762293 Training Time: 0.3167310459445221 (+/-) 0.014903033282089268 === Average network evolution === Total hidden node: 9.303030303030303 (+/-) 2.4056102166047686 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=3, out_features=14, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=14, out_features=2, bias=True) ) No. of inputs : 3 No. of nodes : 14 No. of parameters : 86 Voting weight: [1.0]
100% (100 of 100) |######################| Elapsed Time: 0:00:31 ETA: 00:00:00
=== Performance result === Accuracy: 89.86464646464647 (+/-) 9.795632021120156 Testing Loss: 0.29094100367240233 (+/-) 0.17510082852756947 Precision: 0.9008028037053026 Recall: 0.8986464646464647 F1 score: 0.8967111551403387 Testing Time: 0.003875404897362295 (+/-) 0.005090700992513294 Training Time: 0.31470381370698564 (+/-) 0.01212607451383069 === Average network evolution === Total hidden node: 9.343434343434344 (+/-) 3.1435732617118726 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=3, out_features=15, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=15, out_features=2, bias=True) ) No. of inputs : 3 No. of nodes : 15 No. of parameters : 92 Voting weight: [1.0]
Mean Accuracy: 88.87755102040816 Std Accuracy: 10.539332846989975 Hidden Node mean 7.844897959183673 Hidden Node std: 3.54165078680975 Hidden Layer mean: 1.0 Hidden Layer std: 0.0 Infinite Delay
87% (87 of 100) |#################### | Elapsed Time: 0:00:00 ETA: 0:00:00C:\Users\SCSE\AppData\Local\Continuum\miniconda3\envs\stmicro\lib\site-packages\sklearn\metrics\_classification.py:1272: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior. _warn_prf(average, modifier, msg_start, len(result))
=== Performance result === Accuracy: 63.03636363636363 (+/-) 7.379461732655587 Testing Loss: 0.6052399422183181 (+/-) 0.04699389579780294 Precision: 0.3973583140495867 Recall: 0.6303636363636363 F1 score: 0.4874474690025041 Testing Time: 0.003083043628268772 (+/-) 0.00533707125976596 Training Time: 0.0 (+/-) 0.0 === Average network evolution === Total hidden node: 5.0 (+/-) 0.0 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=3, out_features=5, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=5, out_features=2, bias=True) ) No. of inputs : 3 No. of nodes : 5 No. of parameters : 32 Voting weight: [1.0]
88% (88 of 100) |#################### | Elapsed Time: 0:00:00 ETA: 0:00:00
=== Performance result === Accuracy: 71.99292929292929 (+/-) 7.030672375065245 Testing Loss: 0.5526376333501604 (+/-) 0.037641174592493255 Precision: 0.7848681601356409 Recall: 0.719929292929293 F1 score: 0.6650847450042424 Testing Time: 0.003424545731207337 (+/-) 0.006346452159494795 Training Time: 0.0 (+/-) 0.0 === Average network evolution === Total hidden node: 7.0 (+/-) 0.0 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=3, out_features=7, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=7, out_features=2, bias=True) ) No. of inputs : 3 No. of nodes : 7 No. of parameters : 44 Voting weight: [1.0]
95% (95 of 100) |##################### | Elapsed Time: 0:00:00 ETA: 0:00:00C:\Users\SCSE\AppData\Local\Continuum\miniconda3\envs\stmicro\lib\site-packages\sklearn\metrics\_classification.py:1272: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior. _warn_prf(average, modifier, msg_start, len(result))
=== Performance result === Accuracy: 63.03636363636363 (+/-) 7.379461732655587 Testing Loss: 0.5988696964100154 (+/-) 0.06342261963084407 Precision: 0.3973583140495867 Recall: 0.6303636363636363 F1 score: 0.4874474690025041 Testing Time: 0.0029216270254115865 (+/-) 0.005074020210044609 Training Time: 0.0 (+/-) 0.0 === Average network evolution === Total hidden node: 4.0 (+/-) 0.0 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=3, out_features=4, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=4, out_features=2, bias=True) ) No. of inputs : 3 No. of nodes : 4 No. of parameters : 26 Voting weight: [1.0]
92% (92 of 100) |##################### | Elapsed Time: 0:00:00 ETA: 0:00:00
=== Performance result === Accuracy: 63.5060606060606 (+/-) 6.988559455928966 Testing Loss: 0.617055017538745 (+/-) 0.03424064358230706 Precision: 0.6383223715619244 Recall: 0.6350606060606061 F1 score: 0.5079429566450805 Testing Time: 0.0033042310464261758 (+/-) 0.006985716885186875 Training Time: 0.0 (+/-) 0.0 === Average network evolution === Total hidden node: 4.0 (+/-) 0.0 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=3, out_features=4, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=4, out_features=2, bias=True) ) No. of inputs : 3 No. of nodes : 4 No. of parameters : 26 Voting weight: [1.0]
97% (97 of 100) |###################### | Elapsed Time: 0:00:00 ETA: 0:00:00
=== Performance result === Accuracy: 63.91313131313131 (+/-) 7.405030319536977 Testing Loss: 0.5881666679574986 (+/-) 0.04031304123673675 Precision: 0.7535737633047251 Recall: 0.6391313131313131 F1 score: 0.5079612440573773 Testing Time: 0.0030230921928328697 (+/-) 0.005692165210033363 Training Time: 0.0 (+/-) 0.0 === Average network evolution === Total hidden node: 5.0 (+/-) 0.0 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=3, out_features=5, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=5, out_features=2, bias=True) ) No. of inputs : 3 No. of nodes : 5 No. of parameters : 32 Voting weight: [1.0]
Mean Accuracy: 65.08816326530612 Std Accuracy: 8.057255742235903 Hidden Node mean 5.0 Hidden Node std: 1.0954451150103321 Hidden Layer mean: 1.0 Hidden Layer std: 0.0
In [2]:
%run ADL_hyperplane.ipynb
Number of input: 4 Number of output: 2 Number of batch: 120 All labeled
100% (120 of 120) |######################| Elapsed Time: 0:02:36 ETA: 00:00:00
=== Performance result === Accuracy: 92.1327731092437 (+/-) 2.8999886769902825 Testing Loss: 0.29674529378153697 (+/-) 0.050821148293742575 Precision: 0.9213279873338623 Recall: 0.9213277310924369 F1 score: 0.9213276551809617 Testing Time: 0.003980576491155545 (+/-) 0.006082166285759226 Training Time: 1.3117703650178028 (+/-) 0.23992105310726106 === Average network evolution === Total hidden node: 4.680672268907563 (+/-) 0.5931368415133208 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=4, out_features=5, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=5, out_features=2, bias=True) ) No. of inputs : 4 No. of nodes : 5 No. of parameters : 37 Voting weight: [1.0]
100% (120 of 120) |######################| Elapsed Time: 0:02:38 ETA: 00:00:00
=== Performance result === Accuracy: 92.49747899159662 (+/-) 3.8435466417585946 Testing Loss: 0.2826259513111675 (+/-) 0.06514220485021761 Precision: 0.9249865953720963 Recall: 0.9249747899159664 F1 score: 0.9249739198597343 Testing Time: 0.004233091819186171 (+/-) 0.006687962856221777 Training Time: 1.3240773757966626 (+/-) 0.09279423517343063 === Average network evolution === Total hidden node: 2.7899159663865545 (+/-) 0.46515470598648884 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=4, out_features=4, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=4, out_features=2, bias=True) ) No. of inputs : 4 No. of nodes : 4 No. of parameters : 30 Voting weight: [1.0]
100% (120 of 120) |######################| Elapsed Time: 0:02:36 ETA: 00:00:00
=== Performance result === Accuracy: 92.43109243697484 (+/-) 3.387960589771074 Testing Loss: 0.2825475792173578 (+/-) 0.06330441064276668 Precision: 0.9244009525197152 Recall: 0.9243109243697479 F1 score: 0.9243059525514109 Testing Time: 0.004109683157015247 (+/-) 0.006169050609558756 Training Time: 1.3082366069825757 (+/-) 0.05542289684948646 === Average network evolution === Total hidden node: 2.6050420168067228 (+/-) 0.48884166629408354 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=4, out_features=3, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=3, out_features=2, bias=True) ) No. of inputs : 4 No. of nodes : 3 No. of parameters : 23 Voting weight: [1.0]
100% (120 of 120) |######################| Elapsed Time: 0:02:34 ETA: 00:00:00
=== Performance result === Accuracy: 91.93781512605041 (+/-) 4.986233006596636 Testing Loss: 0.2997847918201895 (+/-) 0.052510714023436 Precision: 0.9195238845219994 Recall: 0.9193781512605042 F1 score: 0.9193698375265501 Testing Time: 0.004584490752019802 (+/-) 0.006870784035579428 Training Time: 1.288882339701933 (+/-) 0.04074106203722367 === Average network evolution === Total hidden node: 6.80672268907563 (+/-) 0.4353557595626426 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=4, out_features=7, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=7, out_features=2, bias=True) ) No. of inputs : 4 No. of nodes : 7 No. of parameters : 51 Voting weight: [1.0]
100% (120 of 120) |######################| Elapsed Time: 0:02:30 ETA: 00:00:00
=== Performance result === Accuracy: 92.27983193277313 (+/-) 3.3536780218551714 Testing Loss: 0.2935772026035966 (+/-) 0.048129877616022 Precision: 0.9227994477380908 Recall: 0.922798319327731 F1 score: 0.9227983673627906 Testing Time: 0.003982660149325843 (+/-) 0.005868431937428219 Training Time: 1.25931769058484 (+/-) 0.019634580561862392 === Average network evolution === Total hidden node: 4.831932773109243 (+/-) 0.37392597413927703 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=4, out_features=5, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=5, out_features=2, bias=True) ) No. of inputs : 4 No. of nodes : 5 No. of parameters : 37 Voting weight: [1.0]
Mean Accuracy: 92.47389830508475 Std Accuracy: 2.824540770803164 Hidden Node mean 4.34406779661017 Hidden Node std: 1.6077957525271356 Hidden Layer mean: 1.0 Hidden Layer std: 0.0 50% labeled
100% (120 of 120) |######################| Elapsed Time: 0:01:17 ETA: 00:00:00
=== Performance result === Accuracy: 91.23529411764706 (+/-) 4.488202803939806 Testing Loss: 0.32004584259345753 (+/-) 0.05771400334108622 Precision: 0.9123541891109385 Recall: 0.9123529411764706 F1 score: 0.9123529958653975 Testing Time: 0.004331318270258543 (+/-) 0.006192188497448879 Training Time: 0.646723781313215 (+/-) 0.020113962363550005 === Average network evolution === Total hidden node: 9.117647058823529 (+/-) 0.3927166872453084 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=4, out_features=9, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=9, out_features=2, bias=True) ) No. of inputs : 4 No. of nodes : 9 No. of parameters : 65 Voting weight: [1.0]
100% (120 of 120) |######################| Elapsed Time: 0:01:17 ETA: 00:00:00
=== Performance result === Accuracy: 91.65798319327732 (+/-) 3.9211663459132384 Testing Loss: 0.30582883716130455 (+/-) 0.07184320426854718 Precision: 0.9165890200747565 Recall: 0.9165798319327731 F1 score: 0.9165790198499257 Testing Time: 0.0039309874302198905 (+/-) 0.005929414859571515 Training Time: 0.6492844469407025 (+/-) 0.022532867927356436 === Average network evolution === Total hidden node: 2.403361344537815 (+/-) 0.8630542572415308 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=4, out_features=2, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=2, out_features=2, bias=True) ) No. of inputs : 4 No. of nodes : 2 No. of parameters : 16 Voting weight: [1.0]
100% (120 of 120) |######################| Elapsed Time: 0:01:19 ETA: 00:00:00
=== Performance result === Accuracy: 91.63949579831933 (+/-) 3.759273541644278 Testing Loss: 0.3139606143246178 (+/-) 0.06598343254852429 Precision: 0.9164031181770563 Recall: 0.9163949579831933 F1 score: 0.9163942149492789 Testing Time: 0.004368551638947816 (+/-) 0.006166941205697606 Training Time: 0.6587371044800061 (+/-) 0.0290957574274117 === Average network evolution === Total hidden node: 7.6722689075630255 (+/-) 0.4693862199586199 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=4, out_features=7, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=7, out_features=2, bias=True) ) No. of inputs : 4 No. of nodes : 7 No. of parameters : 51 Voting weight: [1.0]
100% (120 of 120) |######################| Elapsed Time: 0:01:17 ETA: 00:00:00
=== Performance result === Accuracy: 91.43529411764705 (+/-) 4.322883962568386 Testing Loss: 0.3110736668610773 (+/-) 0.06571033262169357 Precision: 0.9143534667980341 Recall: 0.9143529411764706 F1 score: 0.9143529867791536 Testing Time: 0.004059346784062746 (+/-) 0.006134376617332956 Training Time: 0.6471098130490599 (+/-) 0.028292310142209023 === Average network evolution === Total hidden node: 4.697478991596639 (+/-) 0.47729317045925806 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=4, out_features=5, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=5, out_features=2, bias=True) ) No. of inputs : 4 No. of nodes : 5 No. of parameters : 37 Voting weight: [1.0]
100% (120 of 120) |######################| Elapsed Time: 0:01:16 ETA: 00:00:00
=== Performance result === Accuracy: 91.24285714285713 (+/-) 4.387617630946224 Testing Loss: 0.3104899478058855 (+/-) 0.06589411784119345 Precision: 0.9124408670108138 Recall: 0.9124285714285715 F1 score: 0.9124274879423412 Testing Time: 0.004052428638233858 (+/-) 0.005918169271976022 Training Time: 0.6345747999784326 (+/-) 0.016783416843650017 === Average network evolution === Total hidden node: 4.563025210084033 (+/-) 0.5288111839513367 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=4, out_features=5, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=5, out_features=2, bias=True) ) No. of inputs : 4 No. of nodes : 5 No. of parameters : 37 Voting weight: [1.0]
Mean Accuracy: 91.63050847457627 Std Accuracy: 3.651094762094321 Hidden Node mean 5.688135593220339 Hidden Node std: 2.460748456194848 Hidden Layer mean: 1.0 Hidden Layer std: 0.0 25% labeled
100% (120 of 120) |######################| Elapsed Time: 0:00:38 ETA: 00:00:00
=== Performance result === Accuracy: 89.22689075630252 (+/-) 6.802541510705579 Testing Loss: 0.3611920959308368 (+/-) 0.0915200572070845 Precision: 0.8922693559170953 Recall: 0.8922689075630252 F1 score: 0.892268961363977 Testing Time: 0.0037483427704883224 (+/-) 0.005806303064268548 Training Time: 0.31993593087717265 (+/-) 0.011380686806736444 === Average network evolution === Total hidden node: 2.689075630252101 (+/-) 0.8275497817889198 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=4, out_features=2, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=2, out_features=2, bias=True) ) No. of inputs : 4 No. of nodes : 2 No. of parameters : 16 Voting weight: [1.0]
100% (120 of 120) |######################| Elapsed Time: 0:00:39 ETA: 00:00:00
=== Performance result === Accuracy: 85.35294117647061 (+/-) 10.329754880310379 Testing Loss: 0.42153964723859516 (+/-) 0.15506028011071907 Precision: 0.8535836903111857 Recall: 0.8535294117647059 F1 score: 0.8535254756709769 Testing Time: 0.003788747707334887 (+/-) 0.005751274527775746 Training Time: 0.3282131788109531 (+/-) 0.014660267415140772 === Average network evolution === Total hidden node: 2.134453781512605 (+/-) 0.34113921227200744 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=4, out_features=2, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=2, out_features=2, bias=True) ) No. of inputs : 4 No. of nodes : 2 No. of parameters : 16 Voting weight: [1.0]
100% (120 of 120) |######################| Elapsed Time: 0:00:39 ETA: 00:00:00
=== Performance result === Accuracy: 89.1983193277311 (+/-) 7.8392031750068965 Testing Loss: 0.3487726337268573 (+/-) 0.09833892094931501 Precision: 0.8921083468128961 Recall: 0.8919831932773109 F1 score: 0.8919728178555902 Testing Time: 0.004155715974439092 (+/-) 0.0061491273277764985 Training Time: 0.323298662650485 (+/-) 0.015492256556860663 === Average network evolution === Total hidden node: 5.647058823529412 (+/-) 0.4778846120374095 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=4, out_features=6, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=6, out_features=2, bias=True) ) No. of inputs : 4 No. of nodes : 6 No. of parameters : 44 Voting weight: [1.0]
100% (120 of 120) |######################| Elapsed Time: 0:00:39 ETA: 00:00:00
=== Performance result === Accuracy: 89.6672268907563 (+/-) 6.532917415437297 Testing Loss: 0.34111762622825237 (+/-) 0.08930110145580447 Precision: 0.8968777185912759 Recall: 0.896672268907563 F1 score: 0.8966567772192012 Testing Time: 0.0041334007968421745 (+/-) 0.006064069973112024 Training Time: 0.3240250859941755 (+/-) 0.019959393970618987 === Average network evolution === Total hidden node: 5.100840336134453 (+/-) 0.8239580431432123 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=4, out_features=6, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=6, out_features=2, bias=True) ) No. of inputs : 4 No. of nodes : 6 No. of parameters : 44 Voting weight: [1.0]
100% (120 of 120) |######################| Elapsed Time: 0:00:38 ETA: 00:00:00
=== Performance result === Accuracy: 89.60420168067226 (+/-) 6.869985810389653 Testing Loss: 0.34015305027240467 (+/-) 0.09252488654875712 Precision: 0.8960422946093396 Recall: 0.8960420168067227 F1 score: 0.8960420594661951 Testing Time: 0.004444519010912471 (+/-) 0.006743340048539339 Training Time: 0.31771476529225584 (+/-) 0.011803125587923206 === Average network evolution === Total hidden node: 5.2521008403361344 (+/-) 0.8522682281349981 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=4, out_features=6, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=6, out_features=2, bias=True) ) No. of inputs : 4 No. of nodes : 6 No. of parameters : 44 Voting weight: [1.0]
Mean Accuracy: 88.89406779661017 Std Accuracy: 7.373673881036386 Hidden Node mean 4.16271186440678 Hidden Node std: 1.616849657600534 Hidden Layer mean: 1.0 Hidden Layer std: 0.0 Infinite Delay
96% (116 of 120) |##################### | Elapsed Time: 0:00:00 ETA: 0:00:00
=== Performance result === Accuracy: 72.33361344537816 (+/-) 2.6420732027252227 Testing Loss: 0.6355133692757422 (+/-) 0.007198295135825457 Precision: 0.7233570865729828 Recall: 0.7233361344537815 F1 score: 0.7233327448894931 Testing Time: 0.0032512260084392643 (+/-) 0.00626940860053139 Training Time: 0.0 (+/-) 0.0 === Average network evolution === Total hidden node: 4.0 (+/-) 0.0 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=4, out_features=4, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=4, out_features=2, bias=True) ) No. of inputs : 4 No. of nodes : 4 No. of parameters : 30 Voting weight: [1.0]
96% (116 of 120) |##################### | Elapsed Time: 0:00:00 ETA: 0:00:00
=== Performance result === Accuracy: 59.162184873949585 (+/-) 1.6315683848349878 Testing Loss: 0.6379734493103348 (+/-) 0.006076872644249988 Precision: 0.7501416886814637 Recall: 0.5916218487394957 F1 score: 0.5142552738281043 Testing Time: 0.0033873670241411995 (+/-) 0.005715510497239788 Training Time: 0.0 (+/-) 0.0 === Average network evolution === Total hidden node: 6.0 (+/-) 0.0 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=4, out_features=6, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=6, out_features=2, bias=True) ) No. of inputs : 4 No. of nodes : 6 No. of parameters : 44 Voting weight: [1.0]
91% (110 of 120) |#################### | Elapsed Time: 0:00:00 ETA: 0:00:00
=== Performance result === Accuracy: 75.77563025210084 (+/-) 3.1907156908112344 Testing Loss: 0.5996591348608001 (+/-) 0.011213254420422465 Precision: 0.7654742181221579 Recall: 0.7577563025210085 F1 score: 0.7560300598258421 Testing Time: 0.0035610980346423237 (+/-) 0.006303100160741767 Training Time: 0.0 (+/-) 0.0 === Average network evolution === Total hidden node: 7.0 (+/-) 0.0 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=4, out_features=7, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=7, out_features=2, bias=True) ) No. of inputs : 4 No. of nodes : 7 No. of parameters : 51 Voting weight: [1.0]
91% (110 of 120) |#################### | Elapsed Time: 0:00:00 ETA: 0:00:00
=== Performance result === Accuracy: 70.87058823529411 (+/-) 1.5395269895192576 Testing Loss: 0.6155929665605561 (+/-) 0.005537559541700183 Precision: 0.7936655836740353 Recall: 0.7087058823529412 F1 score: 0.6861784988827916 Testing Time: 0.003395433185481224 (+/-) 0.006682583876897558 Training Time: 0.0 (+/-) 0.0 === Average network evolution === Total hidden node: 5.0 (+/-) 0.0 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=4, out_features=5, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=5, out_features=2, bias=True) ) No. of inputs : 4 No. of nodes : 5 No. of parameters : 37 Voting weight: [1.0]
99% (119 of 120) |##################### | Elapsed Time: 0:00:00 ETA: 0:00:00
=== Performance result === Accuracy: 62.73277310924369 (+/-) 1.6649177557448698 Testing Loss: 0.6535219209534782 (+/-) 0.005991285437134587 Precision: 0.7242308977263545 Recall: 0.627327731092437 F1 score: 0.5818200776223557 Testing Time: 0.0037464875133097673 (+/-) 0.007757471119442078 Training Time: 0.0 (+/-) 0.0 === Average network evolution === Total hidden node: 4.0 (+/-) 0.0 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=4, out_features=4, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=4, out_features=2, bias=True) ) No. of inputs : 4 No. of nodes : 4 No. of parameters : 30 Voting weight: [1.0]
Mean Accuracy: 68.1820338983051 Std Accuracy: 6.587017220507145 Hidden Node mean 5.2 Hidden Node std: 1.16619037896906 Hidden Layer mean: 1.0 Hidden Layer std: 0.0
In [3]:
%run ADL_weather.ipynb
Number of input: 8 Number of output: 2 Number of batch: 18 All labeled
100% (18 of 18) |########################| Elapsed Time: 0:00:21 ETA: 00:00:00
=== Performance result === Accuracy: 71.28823529411765 (+/-) 3.5106363346334284 Testing Loss: 0.5447211931733524 (+/-) 0.0446058537811574 Precision: 0.6906965967572122 Recall: 0.7128823529411765 F1 score: 0.6881400855055277 Testing Time: 0.0024969437543083638 (+/-) 0.0005008489421290735 Training Time: 1.2536747595843147 (+/-) 0.017878871100577967 === Average network evolution === Total hidden node: 7.117647058823529 (+/-) 0.47058823529411764 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=8, out_features=9, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=9, out_features=2, bias=True) ) No. of inputs : 8 No. of nodes : 9 No. of parameters : 101 Voting weight: [1.0]
100% (18 of 18) |########################| Elapsed Time: 0:00:21 ETA: 00:00:00
=== Performance result === Accuracy: 71.8294117647059 (+/-) 2.9511243532079234 Testing Loss: 0.541138116051169 (+/-) 0.032101969186811824 Precision: 0.6969625860043405 Recall: 0.7182941176470589 F1 score: 0.6904015172559538 Testing Time: 0.002802414052626666 (+/-) 0.0005158063836586612 Training Time: 1.2623528732972986 (+/-) 0.020901295079057226 === Average network evolution === Total hidden node: 5.176470588235294 (+/-) 0.3812200410828153 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=8, out_features=6, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=6, out_features=2, bias=True) ) No. of inputs : 8 No. of nodes : 6 No. of parameters : 68 Voting weight: [1.0]
100% (18 of 18) |########################| Elapsed Time: 0:00:21 ETA: 00:00:00
=== Performance result === Accuracy: 71.9470588235294 (+/-) 3.4337627529575507 Testing Loss: 0.5376740010345683 (+/-) 0.04287728052833601 Precision: 0.6984483033781103 Recall: 0.7194705882352941 F1 score: 0.6906652570618736 Testing Time: 0.005447780384736902 (+/-) 0.010121669242366281 Training Time: 1.2635347422431498 (+/-) 0.027621743061962033 === Average network evolution === Total hidden node: 8.058823529411764 (+/-) 0.23529411764705882 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=8, out_features=9, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=9, out_features=2, bias=True) ) No. of inputs : 8 No. of nodes : 9 No. of parameters : 101 Voting weight: [1.0]
100% (18 of 18) |########################| Elapsed Time: 0:00:21 ETA: 00:00:00
=== Performance result === Accuracy: 71.12941176470588 (+/-) 2.849512797548205 Testing Loss: 0.5566502301131978 (+/-) 0.041308765620337654 Precision: 0.686943425161547 Recall: 0.7112941176470589 F1 score: 0.677979788144965 Testing Time: 0.005564381094539867 (+/-) 0.01034121925005352 Training Time: 1.2668095195994657 (+/-) 0.017857610201188787 === Average network evolution === Total hidden node: 7.470588235294118 (+/-) 0.6056253024110001 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=8, out_features=9, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=9, out_features=2, bias=True) ) No. of inputs : 8 No. of nodes : 9 No. of parameters : 101 Voting weight: [1.0]
100% (18 of 18) |########################| Elapsed Time: 0:00:21 ETA: 00:00:00
=== Performance result === Accuracy: 71.41764705882352 (+/-) 2.9945509914072943 Testing Loss: 0.5408432150588316 (+/-) 0.03668811205538584 Precision: 0.6910045857091238 Recall: 0.7141764705882353 F1 score: 0.6779933092886355 Testing Time: 0.004869236665613511 (+/-) 0.009516292548315352 Training Time: 1.2627655898823458 (+/-) 0.025571197862122575 === Average network evolution === Total hidden node: 6.0588235294117645 (+/-) 0.5391265523477459 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=8, out_features=8, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=8, out_features=2, bias=True) ) No. of inputs : 8 No. of nodes : 8 No. of parameters : 90 Voting weight: [1.0]
Mean Accuracy: 71.44875 Std Accuracy: 3.258718833759672 Hidden Node mean 6.8 Hidden Node std: 1.1224972160321824 Hidden Layer mean: 1.0 Hidden Layer std: 0.0 50% labeled
100% (18 of 18) |########################| Elapsed Time: 0:00:10 ETA: 00:00:00
=== Performance result === Accuracy: 68.8 (+/-) 3.6320469030399862 Testing Loss: 0.587289950426887 (+/-) 0.029988123771981533 Precision: 0.6418107060755336 Recall: 0.688 F1 score: 0.6075096455571712 Testing Time: 0.0028778945698457606 (+/-) 0.00046956275967809775 Training Time: 0.6353792442994959 (+/-) 0.018875720767487236 === Average network evolution === Total hidden node: 5.9411764705882355 (+/-) 0.23529411764705882 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=8, out_features=6, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=6, out_features=2, bias=True) ) No. of inputs : 8 No. of nodes : 6 No. of parameters : 68 Voting weight: [1.0]
100% (18 of 18) |########################| Elapsed Time: 0:00:10 ETA: 00:00:00C:\Users\SCSE\AppData\Local\Continuum\miniconda3\envs\stmicro\lib\site-packages\sklearn\metrics\_classification.py:1272: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior. _warn_prf(average, modifier, msg_start, len(result))
=== Performance result === Accuracy: 68.60000000000001 (+/-) 4.105806505282918 Testing Loss: 0.6037568239604726 (+/-) 0.04618104923153804 Precision: 0.470596 Recall: 0.686 F1 score: 0.5582396204033215 Testing Time: 0.0026931902941535503 (+/-) 0.0006663862507812772 Training Time: 0.6336122540866628 (+/-) 0.011524882364522614 === Average network evolution === Total hidden node: 2.1176470588235294 (+/-) 0.32218973970892123 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=8, out_features=2, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=2, out_features=2, bias=True) ) No. of inputs : 8 No. of nodes : 2 No. of parameters : 24 Voting weight: [1.0]
100% (18 of 18) |########################| Elapsed Time: 0:00:10 ETA: 00:00:00
=== Performance result === Accuracy: 69.8 (+/-) 3.145304623795698 Testing Loss: 0.5758455080144546 (+/-) 0.031821676907984965 Precision: 0.668073010473592 Recall: 0.698 F1 score: 0.6260377468356028 Testing Time: 0.002924021552590763 (+/-) 0.0004133982146249562 Training Time: 0.635547539767097 (+/-) 0.017425422864793136 === Average network evolution === Total hidden node: 6.294117647058823 (+/-) 0.4556450995538137 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=8, out_features=6, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=6, out_features=2, bias=True) ) No. of inputs : 8 No. of nodes : 6 No. of parameters : 68 Voting weight: [1.0]
100% (18 of 18) |########################| Elapsed Time: 0:00:10 ETA: 00:00:00
=== Performance result === Accuracy: 70.21176470588236 (+/-) 3.11993256958453 Testing Loss: 0.5660208586384269 (+/-) 0.03237144529787478 Precision: 0.674552825912901 Recall: 0.7021176470588235 F1 score: 0.639975261245551 Testing Time: 0.005148032132317038 (+/-) 0.009450001721434198 Training Time: 0.6321498646455652 (+/-) 0.013014187224119275 === Average network evolution === Total hidden node: 8.058823529411764 (+/-) 0.23529411764705882 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=8, out_features=9, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=9, out_features=2, bias=True) ) No. of inputs : 8 No. of nodes : 9 No. of parameters : 101 Voting weight: [1.0]
100% (18 of 18) |########################| Elapsed Time: 0:00:11 ETA: 00:00:00
=== Performance result === Accuracy: 70.8529411764706 (+/-) 2.8350988460947923 Testing Loss: 0.5595578113022972 (+/-) 0.034596745088238914 Precision: 0.6862030235766621 Recall: 0.7085294117647059 F1 score: 0.6517578418853633 Testing Time: 0.0049100483165067784 (+/-) 0.009256207439080035 Training Time: 0.6420904187595143 (+/-) 0.028351118303813747 === Average network evolution === Total hidden node: 6.588235294117647 (+/-) 0.49215295678475035 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=8, out_features=6, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=6, out_features=2, bias=True) ) No. of inputs : 8 No. of nodes : 6 No. of parameters : 68 Voting weight: [1.0]
Mean Accuracy: 69.4625 Std Accuracy: 3.523470412817454 Hidden Node mean 5.8125 Hidden Node std: 2.0315865105872306 Hidden Layer mean: 1.0 Hidden Layer std: 0.0 25% labeled
100% (18 of 18) |########################| Elapsed Time: 0:00:05 ETA: 00:00:00
=== Performance result === Accuracy: 68.74117647058824 (+/-) 3.9422386628336556 Testing Loss: 0.6158314803067375 (+/-) 0.030927392092747884 Precision: 0.6404650433944069 Recall: 0.6874117647058824 F1 score: 0.5805847981727883 Testing Time: 0.0027942657470703125 (+/-) 0.0003813975455210023 Training Time: 0.32602426585029154 (+/-) 0.008471772957877662 === Average network evolution === Total hidden node: 6.0 (+/-) 0.0 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=8, out_features=6, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=6, out_features=2, bias=True) ) No. of inputs : 8 No. of nodes : 6 No. of parameters : 68 Voting weight: [1.0]
100% (18 of 18) |########################| Elapsed Time: 0:00:05 ETA: 00:00:00
=== Performance result === Accuracy: 68.40588235294116 (+/-) 4.256824360156053 Testing Loss: 0.6017854248776155 (+/-) 0.031852880827710185 Precision: 0.6106257981255584 Recall: 0.6840588235294117 F1 score: 0.5700357135549584 Testing Time: 0.0026844108805936925 (+/-) 0.0005736784881599483 Training Time: 0.3185214154860553 (+/-) 0.01075346024773728 === Average network evolution === Total hidden node: 4.9411764705882355 (+/-) 0.23529411764705882 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=8, out_features=5, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=5, out_features=2, bias=True) ) No. of inputs : 8 No. of nodes : 5 No. of parameters : 57 Voting weight: [1.0]
100% (18 of 18) |########################| Elapsed Time: 0:00:05 ETA: 00:00:00
=== Performance result === Accuracy: 68.59411764705884 (+/-) 4.108308738646784 Testing Loss: 0.5901334425982308 (+/-) 0.0328028741189406 Precision: 0.6256501010651587 Recall: 0.6859411764705883 F1 score: 0.5616446520527002 Testing Time: 0.0025049377890194163 (+/-) 0.0005033900762385822 Training Time: 0.33699708826401653 (+/-) 0.027320601358832443 === Average network evolution === Total hidden node: 2.823529411764706 (+/-) 0.38122004108281526 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=8, out_features=2, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=2, out_features=2, bias=True) ) No. of inputs : 8 No. of nodes : 2 No. of parameters : 24 Voting weight: [1.0]
100% (18 of 18) |########################| Elapsed Time: 0:00:05 ETA: 00:00:00
=== Performance result === Accuracy: 69.20588235294117 (+/-) 3.3282163723912674 Testing Loss: 0.5876201917143429 (+/-) 0.02767136397522674 Precision: 0.6535588183741049 Recall: 0.6920588235294117 F1 score: 0.6129351984547017 Testing Time: 0.005266666412353516 (+/-) 0.009168843906099539 Training Time: 0.32491106145522175 (+/-) 0.012361018050410573 === Average network evolution === Total hidden node: 7.176470588235294 (+/-) 0.3812200410828154 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=8, out_features=7, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=7, out_features=2, bias=True) ) No. of inputs : 8 No. of nodes : 7 No. of parameters : 79 Voting weight: [1.0]
100% (18 of 18) |########################| Elapsed Time: 0:00:05 ETA: 00:00:00
=== Performance result === Accuracy: 68.51176470588236 (+/-) 4.150532545978276 Testing Loss: 0.5968040368136238 (+/-) 0.02931462935797009 Precision: 0.6239822366053435 Recall: 0.6851176470588235 F1 score: 0.57615607694714 Testing Time: 0.005026340484619141 (+/-) 0.008980994083083465 Training Time: 0.3277925042545094 (+/-) 0.012116460751914505 === Average network evolution === Total hidden node: 6.647058823529412 (+/-) 0.47788461203740945 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=8, out_features=7, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=7, out_features=2, bias=True) ) No. of inputs : 8 No. of nodes : 7 No. of parameters : 79 Voting weight: [1.0]
Mean Accuracy: 68.44125 Std Accuracy: 3.971199244246 Hidden Node mean 5.525 Hidden Node std: 1.565047922588954 Hidden Layer mean: 1.0 Hidden Layer std: 0.0 Infinite Delay
N/A% (0 of 18) | | Elapsed Time: 0:00:00 ETA: --:--:--C:\Users\SCSE\AppData\Local\Continuum\miniconda3\envs\stmicro\lib\site-packages\sklearn\metrics\_classification.py:1272: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior. _warn_prf(average, modifier, msg_start, len(result))
=== Performance result === Accuracy: 68.60000000000001 (+/-) 4.105806505282918 Testing Loss: 0.6114419172791874 (+/-) 0.042625517355778825 Precision: 0.470596 Recall: 0.686 F1 score: 0.5582396204033215 Testing Time: 0.00199278663186466 (+/-) 0.0006832930403184679 Training Time: 0.0 (+/-) 0.0 === Average network evolution === Total hidden node: 5.0 (+/-) 0.0 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=8, out_features=5, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=5, out_features=2, bias=True) ) No. of inputs : 8 No. of nodes : 5 No. of parameters : 57 Voting weight: [1.0]
N/A% (0 of 18) | | Elapsed Time: 0:00:00 ETA: --:--:--C:\Users\SCSE\AppData\Local\Continuum\miniconda3\envs\stmicro\lib\site-packages\sklearn\metrics\_classification.py:1272: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior. _warn_prf(average, modifier, msg_start, len(result))
=== Performance result === Accuracy: 68.60000000000001 (+/-) 4.105806505282918 Testing Loss: 0.6190536688355839 (+/-) 0.04722587376596562 Precision: 0.470596 Recall: 0.686 F1 score: 0.5582396204033215 Testing Time: 0.002169482848223518 (+/-) 0.0003808956359621945 Training Time: 0.0 (+/-) 0.0 === Average network evolution === Total hidden node: 6.0 (+/-) 0.0 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=8, out_features=6, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=6, out_features=2, bias=True) ) No. of inputs : 8 No. of nodes : 6 No. of parameters : 68 Voting weight: [1.0]
N/A% (0 of 18) | | Elapsed Time: 0:00:00 ETA: --:--:--C:\Users\SCSE\AppData\Local\Continuum\miniconda3\envs\stmicro\lib\site-packages\sklearn\metrics\_classification.py:1272: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior. _warn_prf(average, modifier, msg_start, len(result))
=== Performance result === Accuracy: 68.60000000000001 (+/-) 4.105806505282918 Testing Loss: 0.604694829267614 (+/-) 0.029736020023796664 Precision: 0.470596 Recall: 0.686 F1 score: 0.5582396204033215 Testing Time: 0.001641091178445255 (+/-) 0.0005860307650434803 Training Time: 0.0 (+/-) 0.0 === Average network evolution === Total hidden node: 8.0 (+/-) 0.0 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=8, out_features=8, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=8, out_features=2, bias=True) ) No. of inputs : 8 No. of nodes : 8 No. of parameters : 90 Voting weight: [1.0]
55% (10 of 18) |############# | Elapsed Time: 0:00:00 ETA: 00:00:00C:\Users\SCSE\AppData\Local\Continuum\miniconda3\envs\stmicro\lib\site-packages\sklearn\metrics\_classification.py:1272: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior. _warn_prf(average, modifier, msg_start, len(result))
=== Performance result === Accuracy: 68.60000000000001 (+/-) 4.105806505282918 Testing Loss: 0.6358883836690117 (+/-) 0.01901054610216545 Precision: 0.470596 Recall: 0.686 F1 score: 0.5582396204033215 Testing Time: 0.004104880725636202 (+/-) 0.008209694043914615 Training Time: 0.0 (+/-) 0.0 === Average network evolution === Total hidden node: 3.0 (+/-) 0.0 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=8, out_features=3, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=3, out_features=2, bias=True) ) No. of inputs : 8 No. of nodes : 3 No. of parameters : 35 Voting weight: [1.0]
88% (16 of 18) |##################### | Elapsed Time: 0:00:00 ETA: 00:00:00C:\Users\SCSE\AppData\Local\Continuum\miniconda3\envs\stmicro\lib\site-packages\sklearn\metrics\_classification.py:1272: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior. _warn_prf(average, modifier, msg_start, len(result))
=== Performance result === Accuracy: 68.60000000000001 (+/-) 4.105806505282918 Testing Loss: 0.6130610003190882 (+/-) 0.020320980405448164 Precision: 0.470596 Recall: 0.686 F1 score: 0.5582396204033215 Testing Time: 0.0038719317492316753 (+/-) 0.008035594198310014 Training Time: 0.0 (+/-) 0.0 === Average network evolution === Total hidden node: 6.0 (+/-) 0.0 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=8, out_features=6, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=6, out_features=2, bias=True) ) No. of inputs : 8 No. of nodes : 6 No. of parameters : 68 Voting weight: [1.0]
Mean Accuracy: 68.34375 Std Accuracy: 4.098165557600132 Hidden Node mean 5.6 Hidden Node std: 1.624807680927192 Hidden Layer mean: 1.0 Hidden Layer std: 0.0
In [4]:
%run ADL_rfid.ipynb
Number of input: 3 Number of output: 4 Number of batch: 280 All labeled
100% (280 of 280) |######################| Elapsed Time: 0:05:58 ETA: 00:00:00
=== Performance result === Accuracy: 98.41146953405017 (+/-) 6.141090027784853 Testing Loss: 0.0965246818959713 (+/-) 0.17284467521388874 Precision: 0.9841308469045139 Recall: 0.9841146953405018 F1 score: 0.9840860127384184 Testing Time: 0.007006877639387671 (+/-) 0.006994731274461606 Training Time: 1.2744880790778812 (+/-) 0.022834699301133923 === Average network evolution === Total hidden node: 34.01433691756272 (+/-) 10.434287058736738 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=3, out_features=44, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=44, out_features=4, bias=True) ) No. of inputs : 3 No. of nodes : 44 No. of parameters : 356 Voting weight: [1.0]
100% (280 of 280) |######################| Elapsed Time: 0:06:05 ETA: 00:00:00
=== Performance result === Accuracy: 97.04802867383513 (+/-) 9.853936210362207 Testing Loss: 0.13435740113645578 (+/-) 0.251883736862754 Precision: 0.9704735499687195 Recall: 0.9704802867383513 F1 score: 0.9704095529854146 Testing Time: 0.006977005244155938 (+/-) 0.006838161119704925 Training Time: 1.301266676208879 (+/-) 0.10862877520837326 === Average network evolution === Total hidden node: 31.387096774193548 (+/-) 12.059915171213738 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=3, out_features=43, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=43, out_features=4, bias=True) ) No. of inputs : 3 No. of nodes : 43 No. of parameters : 348 Voting weight: [1.0]
100% (280 of 280) |######################| Elapsed Time: 0:06:12 ETA: 00:00:00
=== Performance result === Accuracy: 98.21720430107527 (+/-) 7.3865462849150925 Testing Loss: 0.09239974950096407 (+/-) 0.1817480334189206 Precision: 0.9822011505795067 Recall: 0.9821720430107527 F1 score: 0.9821334631042031 Testing Time: 0.007548198050495544 (+/-) 0.007267964247017353 Training Time: 1.3254282739427354 (+/-) 0.1785320461125022 === Average network evolution === Total hidden node: 36.842293906810035 (+/-) 10.624085190539514 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=3, out_features=47, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=47, out_features=4, bias=True) ) No. of inputs : 3 No. of nodes : 47 No. of parameters : 380 Voting weight: [1.0]
100% (280 of 280) |######################| Elapsed Time: 0:05:54 ETA: 00:00:00
=== Performance result === Accuracy: 98.60860215053765 (+/-) 5.083496156334232 Testing Loss: 0.08971409343757189 (+/-) 0.1642726220065111 Precision: 0.9860681229865902 Recall: 0.9860860215053764 F1 score: 0.9860737663352921 Testing Time: 0.007476118730387807 (+/-) 0.007229839076040581 Training Time: 1.2585441143282 (+/-) 0.020427169435175932 === Average network evolution === Total hidden node: 35.14336917562724 (+/-) 10.297764874404166 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=3, out_features=44, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=44, out_features=4, bias=True) ) No. of inputs : 3 No. of nodes : 44 No. of parameters : 356 Voting weight: [1.0]
100% (280 of 280) |######################| Elapsed Time: 0:05:52 ETA: 00:00:00
=== Performance result === Accuracy: 98.3537634408602 (+/-) 6.0645847628237055 Testing Loss: 0.0999376311377492 (+/-) 0.1833736045447648 Precision: 0.9835077967355159 Recall: 0.9835376344086022 F1 score: 0.9835094556113015 Testing Time: 0.0073757684358986475 (+/-) 0.0074610463853840205 Training Time: 1.2530899808398284 (+/-) 0.020589625964804428 === Average network evolution === Total hidden node: 33.681003584229394 (+/-) 10.207982209277864 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=3, out_features=44, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=44, out_features=4, bias=True) ) No. of inputs : 3 No. of nodes : 44 No. of parameters : 356 Voting weight: [1.0]
Mean Accuracy: 98.35050359712228 Std Accuracy: 6.062120544973156 Hidden Node mean 34.313669064748204 Hidden Node std: 10.785856722717943 Hidden Layer mean: 1.0 Hidden Layer std: 0.0 50% labeled
100% (280 of 280) |######################| Elapsed Time: 0:02:57 ETA: 00:00:00
=== Performance result === Accuracy: 96.4010752688172 (+/-) 11.40038194628655 Testing Loss: 0.1934991893241696 (+/-) 0.26474521303583715 Precision: 0.9640247995857536 Recall: 0.964010752688172 F1 score: 0.9640098803310996 Testing Time: 0.006720724926199964 (+/-) 0.0070109531001696914 Training Time: 0.6276418581658367 (+/-) 0.015504405852863641 === Average network evolution === Total hidden node: 25.311827956989248 (+/-) 8.497916878990354 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=3, out_features=35, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=35, out_features=4, bias=True) ) No. of inputs : 3 No. of nodes : 35 No. of parameters : 284 Voting weight: [1.0]
100% (280 of 280) |######################| Elapsed Time: 0:02:58 ETA: 00:00:00
=== Performance result === Accuracy: 97.2874551971326 (+/-) 8.887643166265176 Testing Loss: 0.16569871156339577 (+/-) 0.2294121423009497 Precision: 0.9728148130082398 Recall: 0.9728745519713262 F1 score: 0.9728033593001371 Testing Time: 0.00688018679191562 (+/-) 0.006612166765035878 Training Time: 0.6289730687295237 (+/-) 0.014261620071242511 === Average network evolution === Total hidden node: 28.781362007168457 (+/-) 8.871375393406758 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=3, out_features=39, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=39, out_features=4, bias=True) ) No. of inputs : 3 No. of nodes : 39 No. of parameters : 316 Voting weight: [1.0]
100% (280 of 280) |######################| Elapsed Time: 0:02:57 ETA: 00:00:00
=== Performance result === Accuracy: 96.6247311827957 (+/-) 10.543502535508198 Testing Loss: 0.18553328344524975 (+/-) 0.26440062345039544 Precision: 0.9663343437674362 Recall: 0.966247311827957 F1 score: 0.9661035537325324 Testing Time: 0.006583026660385952 (+/-) 0.006271520355453724 Training Time: 0.6265867328985617 (+/-) 0.015350101266807947 === Average network evolution === Total hidden node: 24.483870967741936 (+/-) 9.349003247304907 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=3, out_features=35, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=35, out_features=4, bias=True) ) No. of inputs : 3 No. of nodes : 35 No. of parameters : 284 Voting weight: [1.0]
100% (280 of 280) |######################| Elapsed Time: 0:02:58 ETA: 00:00:00
=== Performance result === Accuracy: 96.97634408602151 (+/-) 9.947850377648685 Testing Loss: 0.1638026074656556 (+/-) 0.24087922789386126 Precision: 0.9697826733550973 Recall: 0.969763440860215 F1 score: 0.9696495855052154 Testing Time: 0.0071347033251143695 (+/-) 0.007121345875750086 Training Time: 0.6299593089729227 (+/-) 0.021357610810543378 === Average network evolution === Total hidden node: 27.634408602150536 (+/-) 9.24162115474397 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=3, out_features=38, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=38, out_features=4, bias=True) ) No. of inputs : 3 No. of nodes : 38 No. of parameters : 308 Voting weight: [1.0]
100% (280 of 280) |######################| Elapsed Time: 0:02:59 ETA: 00:00:00
=== Performance result === Accuracy: 96.86308243727599 (+/-) 10.70074692551008 Testing Loss: 0.16308473168762141 (+/-) 0.2508491187722539 Precision: 0.9686463793230913 Recall: 0.9686308243727598 F1 score: 0.9685916523727954 Testing Time: 0.007133259140889705 (+/-) 0.007310075773317006 Training Time: 0.6325048665419274 (+/-) 0.020206184373702977 === Average network evolution === Total hidden node: 28.752688172043012 (+/-) 9.77487370026684 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=3, out_features=39, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=39, out_features=4, bias=True) ) No. of inputs : 3 No. of nodes : 39 No. of parameters : 316 Voting weight: [1.0]
Mean Accuracy: 97.07129496402877 Std Accuracy: 9.535294703660611 Hidden Node mean 27.062589928057555 Hidden Node std: 9.271971947534666 Hidden Layer mean: 1.0 Hidden Layer std: 0.0 25% labeled
100% (280 of 280) |######################| Elapsed Time: 0:01:30 ETA: 00:00:00
=== Performance result === Accuracy: 94.85913978494624 (+/-) 12.84661848225006 Testing Loss: 0.30868953629313406 (+/-) 0.2988003275884461 Precision: 0.9485775169310373 Recall: 0.9485913978494623 F1 score: 0.9483909461485568 Testing Time: 0.006202632808343484 (+/-) 0.006954339840470981 Training Time: 0.3159602901841577 (+/-) 0.010865868483907633 === Average network evolution === Total hidden node: 18.157706093189965 (+/-) 7.032709275657048 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=3, out_features=28, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=28, out_features=4, bias=True) ) No. of inputs : 3 No. of nodes : 28 No. of parameters : 228 Voting weight: [1.0]
100% (280 of 280) |######################| Elapsed Time: 0:01:30 ETA: 00:00:00
=== Performance result === Accuracy: 94.85698924731183 (+/-) 13.562295387151217 Testing Loss: 0.3015872121231103 (+/-) 0.30787954199654205 Precision: 0.9484695656524856 Recall: 0.9485698924731183 F1 score: 0.9484659510032419 Testing Time: 0.005951648971940454 (+/-) 0.006345126446401811 Training Time: 0.3165681020333348 (+/-) 0.012128572358553818 === Average network evolution === Total hidden node: 16.978494623655912 (+/-) 7.258630005848145 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=3, out_features=27, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=27, out_features=4, bias=True) ) No. of inputs : 3 No. of nodes : 27 No. of parameters : 220 Voting weight: [1.0]
100% (280 of 280) |######################| Elapsed Time: 0:01:30 ETA: 00:00:00
=== Performance result === Accuracy: 94.43405017921147 (+/-) 13.952765494985412 Testing Loss: 0.3004848081685309 (+/-) 0.31466128756713013 Precision: 0.9442726012091563 Recall: 0.9443405017921147 F1 score: 0.944000619121992 Testing Time: 0.006218871762675624 (+/-) 0.006886791794787729 Training Time: 0.3158271979260188 (+/-) 0.01184076982518149 === Average network evolution === Total hidden node: 18.68100358422939 (+/-) 7.627673000895444 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=3, out_features=29, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=29, out_features=4, bias=True) ) No. of inputs : 3 No. of nodes : 29 No. of parameters : 236 Voting weight: [1.0]
100% (280 of 280) |######################| Elapsed Time: 0:01:31 ETA: 00:00:00
=== Performance result === Accuracy: 94.12114695340502 (+/-) 15.229946593355777 Testing Loss: 0.3254809337918476 (+/-) 0.3278054731938486 Precision: 0.9411412968255319 Recall: 0.9412114695340502 F1 score: 0.9410556739100882 Testing Time: 0.006053769033014988 (+/-) 0.006684823832240594 Training Time: 0.31703068193141704 (+/-) 0.009610329104591812 === Average network evolution === Total hidden node: 16.29749103942652 (+/-) 6.7739508025764525 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=3, out_features=26, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=26, out_features=4, bias=True) ) No. of inputs : 3 No. of nodes : 26 No. of parameters : 212 Voting weight: [1.0]
100% (280 of 280) |######################| Elapsed Time: 0:01:31 ETA: 00:00:00
=== Performance result === Accuracy: 94.5146953405018 (+/-) 13.423745844798646 Testing Loss: 0.29723196094822285 (+/-) 0.30807067811378264 Precision: 0.9450020458853189 Recall: 0.945146953405018 F1 score: 0.9449517327961431 Testing Time: 0.006530056717575237 (+/-) 0.006574902147571334 Training Time: 0.3188580184854487 (+/-) 0.011226789728393539 === Average network evolution === Total hidden node: 20.365591397849464 (+/-) 7.196850584943727 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=3, out_features=30, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=30, out_features=4, bias=True) ) No. of inputs : 3 No. of nodes : 30 No. of parameters : 244 Voting weight: [1.0]
Mean Accuracy: 94.793309352518 Std Accuracy: 13.277727545043847 Hidden Node mean 18.13956834532374 Hidden Node std: 7.297822861560166 Hidden Layer mean: 1.0 Hidden Layer std: 0.0 Infinite Delay
98% (277 of 280) |##################### | Elapsed Time: 0:00:01 ETA: 0:00:00
=== Performance result === Accuracy: 42.40716845878137 (+/-) 2.095468453525845 Testing Loss: 1.3447480975086117 (+/-) 0.0032307752740695296
C:\Users\SCSE\AppData\Local\Continuum\miniconda3\envs\stmicro\lib\site-packages\sklearn\metrics\_classification.py:1272: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior. _warn_prf(average, modifier, msg_start, len(result))
Precision: 0.30913628633426576 Recall: 0.42407168458781364 F1 score: 0.31673680952970273 Testing Time: 0.004364403345251596 (+/-) 0.006388092798664148 Training Time: 0.0 (+/-) 0.0 === Average network evolution === Total hidden node: 7.0 (+/-) 0.0 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=3, out_features=7, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=7, out_features=4, bias=True) ) No. of inputs : 3 No. of nodes : 7 No. of parameters : 60 Voting weight: [1.0]
98% (277 of 280) |##################### | Elapsed Time: 0:00:01 ETA: 0:00:00
=== Performance result === Accuracy: 31.21111111111111 (+/-) 1.4205299071279713 Testing Loss: 1.353252227161093 (+/-) 0.004727415697957422
C:\Users\SCSE\AppData\Local\Continuum\miniconda3\envs\stmicro\lib\site-packages\sklearn\metrics\_classification.py:1272: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior. _warn_prf(average, modifier, msg_start, len(result))
Precision: 0.20549872350585713 Recall: 0.3121111111111111 F1 score: 0.1951421626018636 Testing Time: 0.004389546678057708 (+/-) 0.006040680977662103 Training Time: 3.5754241396449373e-06 (+/-) 5.961423372302035e-05 === Average network evolution === Total hidden node: 7.0 (+/-) 0.0 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=3, out_features=7, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=7, out_features=4, bias=True) ) No. of inputs : 3 No. of nodes : 7 No. of parameters : 60 Voting weight: [1.0]
98% (277 of 280) |##################### | Elapsed Time: 0:00:01 ETA: 0:00:00
=== Performance result === Accuracy: 25.015412186379926 (+/-) 0.10060262148700942 Testing Loss: 1.417539927267259 (+/-) 0.0034650218389932915
C:\Users\SCSE\AppData\Local\Continuum\miniconda3\envs\stmicro\lib\site-packages\sklearn\metrics\_classification.py:1272: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior. _warn_prf(average, modifier, msg_start, len(result))
Precision: 0.06257708468544854 Recall: 0.25015412186379926 F1 score: 0.10011099206257089 Testing Time: 0.0043865711458267705 (+/-) 0.006557407237715854 Training Time: 1.060834494970178e-05 (+/-) 0.00010176384164200318 === Average network evolution === Total hidden node: 6.0 (+/-) 0.0 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=3, out_features=6, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=6, out_features=4, bias=True) ) No. of inputs : 3 No. of nodes : 6 No. of parameters : 52 Voting weight: [1.0]
100% (280 of 280) |######################| Elapsed Time: 0:00:01 ETA: 00:00:00
=== Performance result === Accuracy: 46.164516129032265 (+/-) 1.4130963354718897 Testing Loss: 1.258284276958862 (+/-) 0.0037313205827181005
C:\Users\SCSE\AppData\Local\Continuum\miniconda3\envs\stmicro\lib\site-packages\sklearn\metrics\_classification.py:1272: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior. _warn_prf(average, modifier, msg_start, len(result))
Precision: 0.24384289115897775 Recall: 0.46164516129032257 F1 score: 0.3190244457410917 Testing Time: 0.004496834184106533 (+/-) 0.006526282092032412 Training Time: 0.0 (+/-) 0.0 === Average network evolution === Total hidden node: 8.0 (+/-) 0.0 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=3, out_features=8, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=8, out_features=4, bias=True) ) No. of inputs : 3 No. of nodes : 8 No. of parameters : 68 Voting weight: [1.0]
98% (277 of 280) |##################### | Elapsed Time: 0:00:01 ETA: 0:00:00
=== Performance result === Accuracy: 45.4752688172043 (+/-) 1.2230453718079113 Testing Loss: 1.3584843331340393 (+/-) 0.003134580110440132
C:\Users\SCSE\AppData\Local\Continuum\miniconda3\envs\stmicro\lib\site-packages\sklearn\metrics\_classification.py:1272: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior. _warn_prf(average, modifier, msg_start, len(result))
Precision: 0.32793047492962757 Recall: 0.454752688172043 F1 score: 0.344701343924272 Testing Time: 0.004483316107035538 (+/-) 0.006144646097160609 Training Time: 0.0 (+/-) 0.0 === Average network evolution === Total hidden node: 5.0 (+/-) 0.0 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=3, out_features=5, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=5, out_features=4, bias=True) ) No. of inputs : 3 No. of nodes : 5 No. of parameters : 44 Voting weight: [1.0]
Mean Accuracy: 38.05410071942446 Std Accuracy: 8.563474032228214 Hidden Node mean 6.6 Hidden Node std: 1.019803902718557 Hidden Layer mean: 1.0 Hidden Layer std: 0.0
In [5]:
%run ADL_pmnist.ipynb
Number of input: 784 Number of output: 10 Number of batch: 69 All labeled
100% (69 of 69) |########################| Elapsed Time: 0:01:32 ETA: 00:00:00
=== Performance result === Accuracy: 83.62941176470589 (+/-) 14.036245714991821 Testing Loss: 0.552230480400955 (+/-) 0.4601719522848934 Precision: 0.8366778012648964 Recall: 0.8362941176470589 F1 score: 0.836128807994261 Testing Time: 0.007289672599119299 (+/-) 0.007909643991656556 Training Time: 1.3507589662776274 (+/-) 0.02316126952822371 === Average network evolution === Total hidden node: 18.0 (+/-) 2.1282414723677108 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=784, out_features=21, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=21, out_features=10, bias=True) ) No. of inputs : 784 No. of nodes : 21 No. of parameters : 16705 Voting weight: [1.0]
100% (69 of 69) |########################| Elapsed Time: 0:01:33 ETA: 00:00:00
=== Performance result === Accuracy: 83.27352941176471 (+/-) 14.133716650859464 Testing Loss: 0.5500972243573736 (+/-) 0.42934932940038917 Precision: 0.8323229148390149 Recall: 0.832735294117647 F1 score: 0.8323599340561967 Testing Time: 0.0076811523998484895 (+/-) 0.008031525499286828 Training Time: 1.3629411634276896 (+/-) 0.026443727340209156 === Average network evolution === Total hidden node: 22.485294117647058 (+/-) 5.598037069468356 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=784, out_features=32, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=32, out_features=10, bias=True) ) No. of inputs : 784 No. of nodes : 32 No. of parameters : 25450 Voting weight: [1.0]
100% (69 of 69) |########################| Elapsed Time: 0:01:33 ETA: 00:00:00
=== Performance result === Accuracy: 84.17352941176469 (+/-) 12.999735491054047 Testing Loss: 0.5271609309403336 (+/-) 0.3901938455706791 Precision: 0.842395720809963 Recall: 0.841735294117647 F1 score: 0.8416488865054185 Testing Time: 0.006790687056148753 (+/-) 0.005347995527207314 Training Time: 1.36243837370592 (+/-) 0.027787686681828197 === Average network evolution === Total hidden node: 20.75 (+/-) 2.493373571028995 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=784, out_features=24, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=24, out_features=10, bias=True) ) No. of inputs : 784 No. of nodes : 24 No. of parameters : 19090 Voting weight: [1.0]
100% (69 of 69) |########################| Elapsed Time: 0:01:32 ETA: 00:00:00
=== Performance result === Accuracy: 83.39264705882353 (+/-) 13.232450266368021 Testing Loss: 0.5556339027688784 (+/-) 0.42317462234461284 Precision: 0.8339532263070639 Recall: 0.8339264705882353 F1 score: 0.8336482969002523 Testing Time: 0.006170244777903837 (+/-) 0.00611739323925471 Training Time: 1.3465271206463085 (+/-) 0.021330209722165726 === Average network evolution === Total hidden node: 16.720588235294116 (+/-) 1.7476504246903657 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=784, out_features=19, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=19, out_features=10, bias=True) ) No. of inputs : 784 No. of nodes : 19 No. of parameters : 15115 Voting weight: [1.0]
100% (69 of 69) |########################| Elapsed Time: 0:01:32 ETA: 00:00:00
=== Performance result === Accuracy: 83.65294117647059 (+/-) 13.627065095396986 Testing Loss: 0.5313457902520895 (+/-) 0.4122060554597495 Precision: 0.836966400681923 Recall: 0.8365294117647059 F1 score: 0.836618124909882 Testing Time: 0.006714179235346177 (+/-) 0.005664544494135549 Training Time: 1.3590740491362179 (+/-) 0.023432576095128933 === Average network evolution === Total hidden node: 23.264705882352942 (+/-) 4.8586419279550785 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=784, out_features=29, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=29, out_features=10, bias=True) ) No. of inputs : 784 No. of nodes : 29 No. of parameters : 23065 Voting weight: [1.0]
Mean Accuracy: 84.50268656716418 Std Accuracy: 11.649962857168328 Hidden Node mean 20.34328358208955 Hidden Node std: 4.4431810535701874 Hidden Layer mean: 1.0 Hidden Layer std: 0.0 50% labeled
100% (69 of 69) |########################| Elapsed Time: 0:00:45 ETA: 00:00:00
=== Performance result === Accuracy: 78.98970588235295 (+/-) 16.4116183711587 Testing Loss: 0.7134335104595212 (+/-) 0.4803386855977398 Precision: 0.7891597852797784 Recall: 0.7898970588235295 F1 score: 0.7890300314984406 Testing Time: 0.006696732605204862 (+/-) 0.0068850353178534635 Training Time: 0.6632042632383459 (+/-) 0.02017481504654941 === Average network evolution === Total hidden node: 13.382352941176471 (+/-) 1.7491965530822653 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=784, out_features=16, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=16, out_features=10, bias=True) ) No. of inputs : 784 No. of nodes : 16 No. of parameters : 12730 Voting weight: [1.0]
100% (69 of 69) |########################| Elapsed Time: 0:00:45 ETA: 00:00:00
=== Performance result === Accuracy: 80.5029411764706 (+/-) 16.29932306956186 Testing Loss: 0.6610048402319936 (+/-) 0.49523816976448815 Precision: 0.8047729169287726 Recall: 0.8050294117647059 F1 score: 0.8043986263177768 Testing Time: 0.006828732350293328 (+/-) 0.007900593862392809 Training Time: 0.6664299228612114 (+/-) 0.015689287860185374 === Average network evolution === Total hidden node: 19.220588235294116 (+/-) 2.909647180123866 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=784, out_features=22, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=22, out_features=10, bias=True) ) No. of inputs : 784 No. of nodes : 22 No. of parameters : 17500 Voting weight: [1.0]
100% (69 of 69) |########################| Elapsed Time: 0:00:45 ETA: 00:00:00
=== Performance result === Accuracy: 80.63970588235294 (+/-) 15.39208295067804 Testing Loss: 0.6500660115305115 (+/-) 0.44443011877182 Precision: 0.8075020667601315 Recall: 0.8063970588235294 F1 score: 0.8063987794105941 Testing Time: 0.006120822008918314 (+/-) 0.005663973018455904 Training Time: 0.6647178635877722 (+/-) 0.014765264387780773 === Average network evolution === Total hidden node: 18.147058823529413 (+/-) 1.8492025776021352 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=784, out_features=21, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=21, out_features=10, bias=True) ) No. of inputs : 784 No. of nodes : 21 No. of parameters : 16705 Voting weight: [1.0]
100% (69 of 69) |########################| Elapsed Time: 0:00:45 ETA: 00:00:00
=== Performance result === Accuracy: 81.02794117647059 (+/-) 14.645756719230754 Testing Loss: 0.6483502214884057 (+/-) 0.4476033750598016 Precision: 0.8096041032492314 Recall: 0.8102794117647059 F1 score: 0.8095383991546553 Testing Time: 0.00608450174331665 (+/-) 0.005764129174285193 Training Time: 0.6617630860384773 (+/-) 0.016135120444542086 === Average network evolution === Total hidden node: 17.102941176470587 (+/-) 1.6639756244887525 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=784, out_features=19, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=19, out_features=10, bias=True) ) No. of inputs : 784 No. of nodes : 19 No. of parameters : 15115 Voting weight: [1.0]
100% (69 of 69) |########################| Elapsed Time: 0:00:45 ETA: 00:00:00
=== Performance result === Accuracy: 78.54411764705884 (+/-) 16.79638776250751 Testing Loss: 0.728066055871108 (+/-) 0.4825004176641091 Precision: 0.7863269703522083 Recall: 0.7854411764705882 F1 score: 0.7851103320811684 Testing Time: 0.005749232628766228 (+/-) 0.005676878708404256 Training Time: 0.6561268357669606 (+/-) 0.013449282345160624 === Average network evolution === Total hidden node: 12.147058823529411 (+/-) 0.9589317874647709 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=784, out_features=14, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=14, out_features=10, bias=True) ) No. of inputs : 784 No. of nodes : 14 No. of parameters : 11140 Voting weight: [1.0]
Mean Accuracy: 80.83462686567165 Std Accuracy: 14.283703095293674 Hidden Node mean 16.04179104477612 Hidden Node std: 3.365059678951457 Hidden Layer mean: 1.0 Hidden Layer std: 0.0 25% labeled
100% (69 of 69) |########################| Elapsed Time: 0:00:23 ETA: 00:00:00
=== Performance result === Accuracy: 75.09705882352942 (+/-) 19.12392996305503 Testing Loss: 0.8722659605829155 (+/-) 0.5292670950656785 Precision: 0.7516246374707763 Recall: 0.7509705882352942 F1 score: 0.7503042395694804 Testing Time: 0.006519692785599653 (+/-) 0.0081515543101675 Training Time: 0.333015361252953 (+/-) 0.009836519703710005 === Average network evolution === Total hidden node: 14.411764705882353 (+/-) 1.1786744064419927 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=784, out_features=15, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=15, out_features=10, bias=True) ) No. of inputs : 784 No. of nodes : 15 No. of parameters : 11935 Voting weight: [1.0]
100% (69 of 69) |########################| Elapsed Time: 0:00:23 ETA: 00:00:00
=== Performance result === Accuracy: 75.64117647058823 (+/-) 18.621123641572773 Testing Loss: 0.8683138732962749 (+/-) 0.5201541385011949 Precision: 0.755873514456058 Recall: 0.7564117647058823 F1 score: 0.7543382285876298 Testing Time: 0.0066058811019448676 (+/-) 0.007617518638133852 Training Time: 0.33164596908232746 (+/-) 0.010653390946010421 === Average network evolution === Total hidden node: 14.088235294117647 (+/-) 1.8844198211342762 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=784, out_features=16, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=16, out_features=10, bias=True) ) No. of inputs : 784 No. of nodes : 16 No. of parameters : 12730 Voting weight: [1.0]
100% (69 of 69) |########################| Elapsed Time: 0:00:23 ETA: 00:00:00
=== Performance result === Accuracy: 73.54705882352941 (+/-) 18.341262309726307 Testing Loss: 0.9202936703667921 (+/-) 0.5331370084082283 Precision: 0.7353030837489376 Recall: 0.7354705882352941 F1 score: 0.7321224642450781 Testing Time: 0.005626128000371596 (+/-) 0.00582289670965057 Training Time: 0.33117961182313804 (+/-) 0.011051418493841867 === Average network evolution === Total hidden node: 12.720588235294118 (+/-) 0.8718740504577435 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=784, out_features=14, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=14, out_features=10, bias=True) ) No. of inputs : 784 No. of nodes : 14 No. of parameters : 11140 Voting weight: [1.0]
100% (69 of 69) |########################| Elapsed Time: 0:00:23 ETA: 00:00:00
=== Performance result === Accuracy: 75.87205882352939 (+/-) 18.39113313839544 Testing Loss: 0.8563937233651385 (+/-) 0.518690581676897 Precision: 0.7589136305240193 Recall: 0.7587205882352941 F1 score: 0.7571520016731739 Testing Time: 0.005658226854660932 (+/-) 0.0059441272209432485 Training Time: 0.33192208584617167 (+/-) 0.011045585181986381 === Average network evolution === Total hidden node: 13.838235294117647 (+/-) 1.1062694879326629 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=784, out_features=15, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=15, out_features=10, bias=True) ) No. of inputs : 784 No. of nodes : 15 No. of parameters : 11935 Voting weight: [1.0]
100% (69 of 69) |########################| Elapsed Time: 0:00:23 ETA: 00:00:00
=== Performance result === Accuracy: 75.95 (+/-) 18.016744662543623 Testing Loss: 0.8309477845973828 (+/-) 0.5059725847734725 Precision: 0.7593572020148537 Recall: 0.7595 F1 score: 0.7573258769021564 Testing Time: 0.005799977218403536 (+/-) 0.005575867648111063 Training Time: 0.3371916027630077 (+/-) 0.012132168664260591 === Average network evolution === Total hidden node: 15.867647058823529 (+/-) 1.4235871402976217 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=784, out_features=18, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=18, out_features=10, bias=True) ) No. of inputs : 784 No. of nodes : 18 No. of parameters : 14320 Voting weight: [1.0]
Mean Accuracy: 76.10955223880599 Std Accuracy: 17.160766554986225 Hidden Node mean 14.211940298507463 Hidden Node std: 1.6750604701100447 Hidden Layer mean: 1.0 Hidden Layer std: 0.0 Infinite Delay
92% (64 of 69) |###################### | Elapsed Time: 0:00:00 ETA: 0:00:00
=== Performance result === Accuracy: 23.144117647058824 (+/-) 20.96783518765701 Testing Loss: 2.0989189428441666 (+/-) 0.3850720411510058 Precision: 0.5059563090839508 Recall: 0.23144117647058823 F1 score: 0.2283668225353558 Testing Time: 0.00488353827420403 (+/-) 0.006495506972959082 Training Time: 0.0 (+/-) 0.0 === Average network evolution === Total hidden node: 13.0 (+/-) 0.0 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=784, out_features=13, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=13, out_features=10, bias=True) ) No. of inputs : 784 No. of nodes : 13 No. of parameters : 10345 Voting weight: [1.0]
98% (68 of 69) |####################### | Elapsed Time: 0:00:00 ETA: 0:00:00C:\Users\SCSE\AppData\Local\Continuum\miniconda3\envs\stmicro\lib\site-packages\sklearn\metrics\_classification.py:1272: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior. _warn_prf(average, modifier, msg_start, len(result))
=== Performance result === Accuracy: 20.539705882352937 (+/-) 19.843951069057336 Testing Loss: 2.156495941035888 (+/-) 0.37661902137790076 Precision: 0.502241499891289 Recall: 0.2053970588235294 F1 score: 0.19696785567150626 Testing Time: 0.005074059261995203 (+/-) 0.006220636236936215 Training Time: 0.0 (+/-) 0.0 === Average network evolution === Total hidden node: 13.0 (+/-) 0.0 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=784, out_features=13, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=13, out_features=10, bias=True) ) No. of inputs : 784 No. of nodes : 13 No. of parameters : 10345 Voting weight: [1.0]
94% (65 of 69) |###################### | Elapsed Time: 0:00:00 ETA: 0:00:00
=== Performance result === Accuracy: 20.85147058823529 (+/-) 22.707361417462238 Testing Loss: 2.17113817264052 (+/-) 0.3787638877617473 Precision: 0.5208692707505422 Recall: 0.20851470588235294 F1 score: 0.21451192981234068 Testing Time: 0.004898828618666705 (+/-) 0.005936488267147047 Training Time: 1.4655730303596047e-05 (+/-) 0.00011996232266435502 === Average network evolution === Total hidden node: 13.0 (+/-) 0.0 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=784, out_features=13, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=13, out_features=10, bias=True) ) No. of inputs : 784 No. of nodes : 13 No. of parameters : 10345 Voting weight: [1.0]
88% (61 of 69) |##################### | Elapsed Time: 0:00:00 ETA: 0:00:00
=== Performance result === Accuracy: 25.68088235294118 (+/-) 23.58522255037813 Testing Loss: 2.0663314812323628 (+/-) 0.37271079248281036 Precision: 0.4596745345436153 Recall: 0.25680882352941176 F1 score: 0.2675956740302738 Testing Time: 0.004575287594514734 (+/-) 0.005590206552787734 Training Time: 0.0 (+/-) 0.0 === Average network evolution === Total hidden node: 13.0 (+/-) 0.0 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=784, out_features=13, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=13, out_features=10, bias=True) ) No. of inputs : 784 No. of nodes : 13 No. of parameters : 10345 Voting weight: [1.0]
91% (63 of 69) |##################### | Elapsed Time: 0:00:00 ETA: 0:00:00C:\Users\SCSE\AppData\Local\Continuum\miniconda3\envs\stmicro\lib\site-packages\sklearn\metrics\_classification.py:1272: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior. _warn_prf(average, modifier, msg_start, len(result))
=== Performance result === Accuracy: 23.110294117647054 (+/-) 24.08607200477855 Testing Loss: 2.099849259152132 (+/-) 0.4145151207936271 Precision: 0.413975226061566 Recall: 0.2311029411764706 F1 score: 0.22408442935146733 Testing Time: 0.004487367237315458 (+/-) 0.004284739165886483 Training Time: 0.0 (+/-) 0.0 === Average network evolution === Total hidden node: 13.0 (+/-) 0.0 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=784, out_features=13, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=13, out_features=10, bias=True) ) No. of inputs : 784 No. of nodes : 13 No. of parameters : 10345 Voting weight: [1.0]
Mean Accuracy: 22.663582089552236 Std Accuracy: 22.538950412033323 Hidden Node mean 13.0 Hidden Node std: 0.0 Hidden Layer mean: 1.0 Hidden Layer std: 0.0
In [6]:
%run ADL_rmnist.ipynb
Number of input: 784 Number of output: 10 Number of batch: 69 All labeled
100% (69 of 69) |########################| Elapsed Time: 0:01:33 ETA: 00:00:00
=== Performance result === Accuracy: 89.56911764705883 (+/-) 4.0122700539917755 Testing Loss: 0.37158865437788124 (+/-) 0.18384539539433573 Precision: 0.8953301748883141 Recall: 0.8956911764705883 F1 score: 0.8952943915392418 Testing Time: 0.007246508317835191 (+/-) 0.007861702456245944 Training Time: 1.3589341956026413 (+/-) 0.024262420094089545 === Average network evolution === Total hidden node: 21.794117647058822 (+/-) 4.333721480265213 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=784, out_features=29, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=29, out_features=10, bias=True) ) No. of inputs : 784 No. of nodes : 29 No. of parameters : 23065 Voting weight: [1.0]
100% (69 of 69) |########################| Elapsed Time: 0:01:32 ETA: 00:00:00
=== Performance result === Accuracy: 88.94558823529411 (+/-) 4.795783498017982 Testing Loss: 0.39259583492051153 (+/-) 0.1960947791522328 Precision: 0.8893137288221734 Recall: 0.8894558823529412 F1 score: 0.8892496341085132 Testing Time: 0.006432056427001953 (+/-) 0.006339450986640934 Training Time: 1.358168766779058 (+/-) 0.02588178101706694 === Average network evolution === Total hidden node: 20.941176470588236 (+/-) 4.850355817576007 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=784, out_features=29, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=29, out_features=10, bias=True) ) No. of inputs : 784 No. of nodes : 29 No. of parameters : 23065 Voting weight: [1.0]
100% (69 of 69) |########################| Elapsed Time: 0:01:33 ETA: 00:00:00
=== Performance result === Accuracy: 89.81764705882352 (+/-) 4.651911092939009 Testing Loss: 0.36535090525798936 (+/-) 0.19268950119153092 Precision: 0.8980069174825702 Recall: 0.8981764705882352 F1 score: 0.8979554496803271 Testing Time: 0.006704547825981589 (+/-) 0.005028431103552435 Training Time: 1.360401707537034 (+/-) 0.03103397707023442 === Average network evolution === Total hidden node: 22.352941176470587 (+/-) 4.831772010478731 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=784, out_features=30, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=30, out_features=10, bias=True) ) No. of inputs : 784 No. of nodes : 30 No. of parameters : 23860 Voting weight: [1.0]
100% (69 of 69) |########################| Elapsed Time: 0:01:32 ETA: 00:00:00
=== Performance result === Accuracy: 89.36470588235294 (+/-) 3.9529127274886635 Testing Loss: 0.38666333181454854 (+/-) 0.19428607323949487 Precision: 0.8933551290104585 Recall: 0.8936470588235295 F1 score: 0.8932763253887217 Testing Time: 0.006505675175610711 (+/-) 0.005244149723956401 Training Time: 1.3457404164706959 (+/-) 0.019674688004044573 === Average network evolution === Total hidden node: 19.147058823529413 (+/-) 2.906709813124843 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=784, out_features=23, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=23, out_features=10, bias=True) ) No. of inputs : 784 No. of nodes : 23 No. of parameters : 18295 Voting weight: [1.0]
100% (69 of 69) |########################| Elapsed Time: 0:01:31 ETA: 00:00:00
=== Performance result === Accuracy: 89.83088235294117 (+/-) 3.926203725234023 Testing Loss: 0.3655843844308573 (+/-) 0.1779091644879075 Precision: 0.8980480452505217 Recall: 0.8983088235294118 F1 score: 0.8979916326669882 Testing Time: 0.006541553665609921 (+/-) 0.0052393677052419265 Training Time: 1.342955298283521 (+/-) 0.03405930998993153 === Average network evolution === Total hidden node: 21.044117647058822 (+/-) 2.783532581669917 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=784, out_features=25, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=25, out_features=10, bias=True) ) No. of inputs : 784 No. of nodes : 25 No. of parameters : 19885 Voting weight: [1.0]
Mean Accuracy: 89.79373134328358 Std Accuracy: 3.5917055507995728 Hidden Node mean 21.170149253731342 Hidden Node std: 4.111614961260797 Hidden Layer mean: 1.0 Hidden Layer std: 0.0 50% labeled
100% (69 of 69) |########################| Elapsed Time: 0:00:46 ETA: 00:00:00
=== Performance result === Accuracy: 86.98382352941178 (+/-) 6.129163897833472 Testing Loss: 0.4804294142214691 (+/-) 0.27243974647002756 Precision: 0.8692266858417849 Recall: 0.8698382352941176 F1 score: 0.869159186963459 Testing Time: 0.006842648281770594 (+/-) 0.008092308218929922 Training Time: 0.6680060134214514 (+/-) 0.01821675302479644 === Average network evolution === Total hidden node: 16.764705882352942 (+/-) 1.70740297337647 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=784, out_features=19, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=19, out_features=10, bias=True) ) No. of inputs : 784 No. of nodes : 19 No. of parameters : 15115 Voting weight: [1.0]
100% (69 of 69) |########################| Elapsed Time: 0:00:45 ETA: 00:00:00
=== Performance result === Accuracy: 87.0235294117647 (+/-) 6.4635657079432285 Testing Loss: 0.46894242329632535 (+/-) 0.2540721369574389 Precision: 0.8701184410601098 Recall: 0.8702352941176471 F1 score: 0.8696154279445064 Testing Time: 0.006566587616415585 (+/-) 0.006823347317057662 Training Time: 0.6680324638591093 (+/-) 0.015447335120051555 === Average network evolution === Total hidden node: 17.08823529411765 (+/-) 1.4114583000825676 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=784, out_features=19, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=19, out_features=10, bias=True) ) No. of inputs : 784 No. of nodes : 19 No. of parameters : 15115 Voting weight: [1.0]
100% (69 of 69) |########################| Elapsed Time: 0:00:46 ETA: 00:00:00
=== Performance result === Accuracy: 87.83529411764705 (+/-) 5.575175141165637 Testing Loss: 0.44894385348786325 (+/-) 0.2416725329025003 Precision: 0.8779035411631845 Recall: 0.8783529411764706 F1 score: 0.8779205800107512 Testing Time: 0.006344065946691176 (+/-) 0.0056232377576093 Training Time: 0.6746709977879244 (+/-) 0.015139351175214637 === Average network evolution === Total hidden node: 19.455882352941178 (+/-) 2.69767777874302 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=784, out_features=25, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=25, out_features=10, bias=True) ) No. of inputs : 784 No. of nodes : 25 No. of parameters : 19885 Voting weight: [1.0]
100% (69 of 69) |########################| Elapsed Time: 0:00:45 ETA: 00:00:00
=== Performance result === Accuracy: 87.28529411764706 (+/-) 6.059321081797724 Testing Loss: 0.4811044517247116 (+/-) 0.25507087215849683 Precision: 0.8725587053236206 Recall: 0.8728529411764706 F1 score: 0.872300683123871 Testing Time: 0.006016629583695356 (+/-) 0.005670217456542084 Training Time: 0.6663284722496482 (+/-) 0.016990761572798496 === Average network evolution === Total hidden node: 17.58823529411765 (+/-) 2.5852255227465566 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=784, out_features=21, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=21, out_features=10, bias=True) ) No. of inputs : 784 No. of nodes : 21 No. of parameters : 16705 Voting weight: [1.0]
100% (69 of 69) |########################| Elapsed Time: 0:00:46 ETA: 00:00:00
=== Performance result === Accuracy: 88.11617647058824 (+/-) 5.42631416162231 Testing Loss: 0.4447358674643671 (+/-) 0.2541047302337785 Precision: 0.8805529631965382 Recall: 0.8811617647058824 F1 score: 0.8806431869139512 Testing Time: 0.006567404550664565 (+/-) 0.0060915653297951835 Training Time: 0.6716056746595046 (+/-) 0.017708610781394855 === Average network evolution === Total hidden node: 23.08823529411765 (+/-) 3.890921915999007 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=784, out_features=30, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=30, out_features=10, bias=True) ) No. of inputs : 784 No. of nodes : 30 No. of parameters : 23860 Voting weight: [1.0]
Mean Accuracy: 87.9002985074627 Std Accuracy: 4.691424367658554 Hidden Node mean 18.86268656716418 Hidden Node std: 3.4854424683628507 Hidden Layer mean: 1.0 Hidden Layer std: 0.0 25% labeled
100% (69 of 69) |########################| Elapsed Time: 0:00:23 ETA: 00:00:00
=== Performance result === Accuracy: 84.00588235294117 (+/-) 9.08226912487994 Testing Loss: 0.6258231723571525 (+/-) 0.36077197450154447 Precision: 0.8391205759758197 Recall: 0.8400588235294117 F1 score: 0.838949776687193 Testing Time: 0.006316497045404771 (+/-) 0.00800372580737738 Training Time: 0.335057605715359 (+/-) 0.011112340488730353 === Average network evolution === Total hidden node: 14.088235294117647 (+/-) 1.4924840536900323 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=784, out_features=16, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=16, out_features=10, bias=True) ) No. of inputs : 784 No. of nodes : 16 No. of parameters : 12730 Voting weight: [1.0]
100% (69 of 69) |########################| Elapsed Time: 0:00:23 ETA: 00:00:00
=== Performance result === Accuracy: 85.18970588235295 (+/-) 7.771557109968041 Testing Loss: 0.5779462419450283 (+/-) 0.3298802443682519 Precision: 0.8517053262382698 Recall: 0.8518970588235294 F1 score: 0.8507589752007055 Testing Time: 0.0070640269447775446 (+/-) 0.007891563918854795 Training Time: 0.3394626729628619 (+/-) 0.010723921175889965 === Average network evolution === Total hidden node: 17.058823529411764 (+/-) 1.7563527796274843 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=784, out_features=20, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=20, out_features=10, bias=True) ) No. of inputs : 784 No. of nodes : 20 No. of parameters : 15910 Voting weight: [1.0]
100% (69 of 69) |########################| Elapsed Time: 0:00:23 ETA: 00:00:00
=== Performance result === Accuracy: 83.65588235294116 (+/-) 9.04751155831944 Testing Loss: 0.6313754193046514 (+/-) 0.35493663555211563 Precision: 0.8357763123128847 Recall: 0.8365588235294118 F1 score: 0.8352559594296709 Testing Time: 0.006006093586192411 (+/-) 0.005781876503660694 Training Time: 0.3373185431256014 (+/-) 0.01201437388570467 === Average network evolution === Total hidden node: 15.308823529411764 (+/-) 2.0238094026537916 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=784, out_features=19, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=19, out_features=10, bias=True) ) No. of inputs : 784 No. of nodes : 19 No. of parameters : 15115 Voting weight: [1.0]
100% (69 of 69) |########################| Elapsed Time: 0:00:23 ETA: 00:00:00
=== Performance result === Accuracy: 84.43529411764705 (+/-) 9.14695006555355 Testing Loss: 0.6096363216638565 (+/-) 0.34431017979233014 Precision: 0.8439272409349576 Recall: 0.8443529411764706 F1 score: 0.8431941179138146 Testing Time: 0.00616295197430779 (+/-) 0.005875579077147709 Training Time: 0.3382856845855713 (+/-) 0.010722130464719688 === Average network evolution === Total hidden node: 15.852941176470589 (+/-) 1.3854783192133975 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=784, out_features=18, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=18, out_features=10, bias=True) ) No. of inputs : 784 No. of nodes : 18 No. of parameters : 14320 Voting weight: [1.0]
100% (69 of 69) |########################| Elapsed Time: 0:00:23 ETA: 00:00:00
=== Performance result === Accuracy: 83.33382352941176 (+/-) 9.673061597795213 Testing Loss: 0.6446357849327957 (+/-) 0.3501172821665198 Precision: 0.8331665191731664 Recall: 0.8333382352941177 F1 score: 0.8320004232468529 Testing Time: 0.005803862038780661 (+/-) 0.004716646188223038 Training Time: 0.33922698217279773 (+/-) 0.011489905682218417 === Average network evolution === Total hidden node: 14.088235294117647 (+/-) 2.084503708162343 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=784, out_features=18, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=18, out_features=10, bias=True) ) No. of inputs : 784 No. of nodes : 18 No. of parameters : 14320 Voting weight: [1.0]
Mean Accuracy: 84.76835820895523 Std Accuracy: 7.328900998228562 Hidden Node mean 15.304477611940298 Hidden Node std: 2.098288772282508 Hidden Layer mean: 1.0 Hidden Layer std: 0.0 Infinite Delay
94% (65 of 69) |###################### | Elapsed Time: 0:00:00 ETA: 0:00:00
=== Performance result === Accuracy: 61.94558823529411 (+/-) 3.3903163926416275 Testing Loss: 1.556813490741393 (+/-) 0.059817927377113965 Precision: 0.6857822839618638 Recall: 0.6194558823529411 F1 score: 0.5920594705056055 Testing Time: 0.005322842036976534 (+/-) 0.007216117088999928 Training Time: 0.0 (+/-) 0.0 === Average network evolution === Total hidden node: 12.0 (+/-) 0.0 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=784, out_features=12, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=12, out_features=10, bias=True) ) No. of inputs : 784 No. of nodes : 12 No. of parameters : 9550 Voting weight: [1.0]
97% (67 of 69) |####################### | Elapsed Time: 0:00:00 ETA: 0:00:00
=== Performance result === Accuracy: 58.622058823529414 (+/-) 3.8926342807408214 Testing Loss: 1.5050830104771782 (+/-) 0.06633649319569002 Precision: 0.703848217816864 Recall: 0.5862205882352941 F1 score: 0.5806317234937073 Testing Time: 0.005249759730170755 (+/-) 0.005997737489061065 Training Time: 1.4666248770321117e-05 (+/-) 0.00012004842002511888 === Average network evolution === Total hidden node: 13.0 (+/-) 0.0 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=784, out_features=13, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=13, out_features=10, bias=True) ) No. of inputs : 784 No. of nodes : 13 No. of parameters : 10345 Voting weight: [1.0]
94% (65 of 69) |###################### | Elapsed Time: 0:00:00 ETA: 0:00:00
=== Performance result === Accuracy: 59.17500000000001 (+/-) 3.3731367405707458 Testing Loss: 1.5079949445584242 (+/-) 0.07260987476581167 Precision: 0.6211730103197828 Recall: 0.59175 F1 score: 0.5418073303087408 Testing Time: 0.004986166954040527 (+/-) 0.005676172448656558 Training Time: 0.0 (+/-) 0.0 === Average network evolution === Total hidden node: 13.0 (+/-) 0.0 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=784, out_features=13, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=13, out_features=10, bias=True) ) No. of inputs : 784 No. of nodes : 13 No. of parameters : 10345 Voting weight: [1.0]
98% (68 of 69) |####################### | Elapsed Time: 0:00:00 ETA: 0:00:00
=== Performance result === Accuracy: 61.8985294117647 (+/-) 5.01226415455304 Testing Loss: 1.4485924717258005 (+/-) 0.07445124422711086 Precision: 0.7156493084169475 Recall: 0.618985294117647 F1 score: 0.6108228086608515 Testing Time: 0.005147741121404311 (+/-) 0.006149533714278105 Training Time: 0.0 (+/-) 0.0 === Average network evolution === Total hidden node: 14.0 (+/-) 0.0 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=784, out_features=14, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=14, out_features=10, bias=True) ) No. of inputs : 784 No. of nodes : 14 No. of parameters : 11140 Voting weight: [1.0]
89% (62 of 69) |##################### | Elapsed Time: 0:00:00 ETA: 0:00:00
=== Performance result === Accuracy: 62.98529411764707 (+/-) 3.392347127158697 Testing Loss: 1.4689970244379604 (+/-) 0.06639035830425101 Precision: 0.6692403696501663 Recall: 0.6298529411764706 F1 score: 0.6107525499796178 Testing Time: 0.0045760729733635395 (+/-) 0.005382071267345738 Training Time: 0.0 (+/-) 0.0 === Average network evolution === Total hidden node: 14.0 (+/-) 0.0 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=784, out_features=14, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=14, out_features=10, bias=True) ) No. of inputs : 784 No. of nodes : 14 No. of parameters : 11140 Voting weight: [1.0]
Mean Accuracy: 60.84507462686568 Std Accuracy: 4.195131995196027 Hidden Node mean 13.2 Hidden Node std: 0.7483314773547882 Hidden Layer mean: 1.0 Hidden Layer std: 0.0
In [7]:
%run ADL_hepmass.ipynb
Number of input: 28 Number of output: 2 Number of batch: 2000 All labeled
100% (2000 of 2000) |####################| Elapsed Time: 0:42:38 ETA: 00:00:00
=== Performance result === Accuracy: 84.13816908454228 (+/-) 1.6914548055163237 Testing Loss: 0.33302605788728007 (+/-) 0.027027352595151925 Precision: 0.8429299153266558 Recall: 0.8413816908454227 F1 score: 0.8412013572268461 Testing Time: 0.012572725514521177 (+/-) 0.009920815689287482 Training Time: 1.2501563833855938 (+/-) 0.02631145327018363 === Average network evolution === Total hidden node: 4.943971985992997 (+/-) 0.32697995222977794 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=28, out_features=5, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=5, out_features=2, bias=True) ) No. of inputs : 28 No. of nodes : 5 No. of parameters : 157 Voting weight: [1.0]
100% (2000 of 2000) |####################| Elapsed Time: 0:42:38 ETA: 00:00:00
=== Performance result === Accuracy: 84.13106553276639 (+/-) 1.6682991417071202 Testing Loss: 0.3331058333372104 (+/-) 0.027592446712496454 Precision: 0.8429554409309027 Recall: 0.8413106553276638 F1 score: 0.8411190244126483 Testing Time: 0.012605977094191322 (+/-) 0.010040343349018072 Training Time: 1.2497497101078157 (+/-) 0.02490994663497221 === Average network evolution === Total hidden node: 4.9289644822411205 (+/-) 0.37686534993961973 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=28, out_features=5, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=5, out_features=2, bias=True) ) No. of inputs : 28 No. of nodes : 5 No. of parameters : 157 Voting weight: [1.0]
100% (2000 of 2000) |####################| Elapsed Time: 0:42:40 ETA: 00:00:00
=== Performance result === Accuracy: 84.15657828914458 (+/-) 1.639649268169928 Testing Loss: 0.33212350627194054 (+/-) 0.0254141726857162 Precision: 0.8432917138778665 Recall: 0.8415657828914457 F1 score: 0.8413652346237308 Testing Time: 0.012782962874450226 (+/-) 0.010160404472267903 Training Time: 1.250524992463349 (+/-) 0.023092571666422177 === Average network evolution === Total hidden node: 4.955977988994497 (+/-) 0.5515570134494715 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=28, out_features=4, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=4, out_features=2, bias=True) ) No. of inputs : 28 No. of nodes : 4 No. of parameters : 126 Voting weight: [1.0]
100% (2000 of 2000) |####################| Elapsed Time: 0:42:48 ETA: 00:00:00
=== Performance result === Accuracy: 84.41970985492746 (+/-) 1.595131323066174 Testing Loss: 0.3284256686235202 (+/-) 0.025356202495859157 Precision: 0.8459054333217425 Recall: 0.8441970985492746 F1 score: 0.8440033660752372 Testing Time: 0.012899168256880821 (+/-) 0.010035063367205081 Training Time: 1.2546261278851858 (+/-) 0.028673484416009688 === Average network evolution === Total hidden node: 6.136068034017009 (+/-) 0.3627127343194688 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=28, out_features=6, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=6, out_features=2, bias=True) ) No. of inputs : 28 No. of nodes : 6 No. of parameters : 188 Voting weight: [1.0]
100% (2000 of 2000) |####################| Elapsed Time: 0:43:01 ETA: 00:00:00
=== Performance result === Accuracy: 84.15092546273137 (+/-) 1.4998141935768579 Testing Loss: 0.33179149991753937 (+/-) 0.02435458658050768 Precision: 0.8429556284650371 Recall: 0.8415092546273136 F1 score: 0.8413409093430227 Testing Time: 0.012693894631031336 (+/-) 0.009880717628207834 Training Time: 1.2614545855538852 (+/-) 0.025257858768041427 === Average network evolution === Total hidden node: 5.986493246623311 (+/-) 0.13902274091190991 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=28, out_features=6, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=6, out_features=2, bias=True) ) No. of inputs : 28 No. of nodes : 6 No. of parameters : 188 Voting weight: [1.0]
Mean Accuracy: 84.21250250250249 Std Accuracy: 1.511312313405934 Hidden Node mean 5.391191191191191 Hidden Node std: 0.6643522005147656 Hidden Layer mean: 1.0 Hidden Layer std: 0.0 50% labeled
100% (2000 of 2000) |####################| Elapsed Time: 0:22:01 ETA: 00:00:00
=== Performance result === Accuracy: 83.52741370685342 (+/-) 2.2991828951662217 Testing Loss: 0.3406173401084049 (+/-) 0.03376605071207909 Precision: 0.8370602682742696 Recall: 0.8352741370685343 F1 score: 0.835054366979639 Testing Time: 0.012215889114448581 (+/-) 0.009667828989623569 Training Time: 0.6316477155136788 (+/-) 0.016212408516869867 === Average network evolution === Total hidden node: 4.630815407703852 (+/-) 0.5999590493301672 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=28, out_features=5, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=5, out_features=2, bias=True) ) No. of inputs : 28 No. of nodes : 5 No. of parameters : 157 Voting weight: [1.0]
100% (2000 of 2000) |####################| Elapsed Time: 0:22:01 ETA: 00:00:00
=== Performance result === Accuracy: 84.07988994497249 (+/-) 1.9425041696527978 Testing Loss: 0.33042013370853596 (+/-) 0.030668149887326093 Precision: 0.8421684676050889 Recall: 0.8407988994497249 F1 score: 0.8406383911720591 Testing Time: 0.01265965800931777 (+/-) 0.009869017161973722 Training Time: 0.6311214277898151 (+/-) 0.01883264589830312 === Average network evolution === Total hidden node: 7.685342671335667 (+/-) 0.4915903789593631 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=28, out_features=8, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=8, out_features=2, bias=True) ) No. of inputs : 28 No. of nodes : 8 No. of parameters : 250 Voting weight: [1.0]
100% (2000 of 2000) |####################| Elapsed Time: 0:21:59 ETA: 00:00:00
=== Performance result === Accuracy: 83.9047523761881 (+/-) 1.8381163625010668 Testing Loss: 0.3364269971370458 (+/-) 0.028807834017877853 Precision: 0.8402684432728482 Recall: 0.839047523761881 F1 score: 0.8389020132857483 Testing Time: 0.012524122712372422 (+/-) 0.00952241768027817 Training Time: 0.6303243031198827 (+/-) 0.016214143355380194 === Average network evolution === Total hidden node: 6.016008004002001 (+/-) 0.28772428567684744 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=28, out_features=6, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=6, out_features=2, bias=True) ) No. of inputs : 28 No. of nodes : 6 No. of parameters : 188 Voting weight: [1.0]
100% (2000 of 2000) |####################| Elapsed Time: 0:22:02 ETA: 00:00:00
=== Performance result === Accuracy: 83.83226613306654 (+/-) 2.1962459255036197 Testing Loss: 0.33874515378815107 (+/-) 0.03485835448217538 Precision: 0.8400007295917159 Recall: 0.8383226613306654 F1 score: 0.8381217443025815 Testing Time: 0.012393322510979306 (+/-) 0.009869821647704436 Training Time: 0.6319127311821041 (+/-) 0.015577827714429233 === Average network evolution === Total hidden node: 4.0945472736368185 (+/-) 0.3995561352224711 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=28, out_features=4, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=4, out_features=2, bias=True) ) No. of inputs : 28 No. of nodes : 4 No. of parameters : 126 Voting weight: [1.0]
100% (2000 of 2000) |####################| Elapsed Time: 0:22:00 ETA: 00:00:00
=== Performance result === Accuracy: 83.86188094047023 (+/-) 1.843601664509068 Testing Loss: 0.33629855118494384 (+/-) 0.028433472825252906 Precision: 0.8400100018947673 Recall: 0.8386188094047023 F1 score: 0.8384524890107581 Testing Time: 0.012502314508885608 (+/-) 0.009890909044901853 Training Time: 0.6310744385769392 (+/-) 0.016823065539712332 === Average network evolution === Total hidden node: 5.290145072536268 (+/-) 0.4690073697938474 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=28, out_features=5, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=5, out_features=2, bias=True) ) No. of inputs : 28 No. of nodes : 5 No. of parameters : 157 Voting weight: [1.0]
Mean Accuracy: 83.85588588588588 Std Accuracy: 1.9318693045858437 Hidden Node mean 5.544044044044044 Hidden Node std: 1.3316100207303079 Hidden Layer mean: 1.0 Hidden Layer std: 0.0 25% labeled
100% (2000 of 2000) |####################| Elapsed Time: 0:11:37 ETA: 00:00:00
=== Performance result === Accuracy: 83.3568284142071 (+/-) 2.564675598693976 Testing Loss: 0.3452682128812505 (+/-) 0.03842571910049675 Precision: 0.8344120475294611 Recall: 0.8335682841420711 F1 score: 0.8334623579425567 Testing Time: 0.012672002939297712 (+/-) 0.010011346109301149 Training Time: 0.3188720054779129 (+/-) 0.011814273829837341 === Average network evolution === Total hidden node: 6.043521760880441 (+/-) 0.5270158216219137 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=28, out_features=7, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=7, out_features=2, bias=True) ) No. of inputs : 28 No. of nodes : 7 No. of parameters : 219 Voting weight: [1.0]
100% (2000 of 2000) |####################| Elapsed Time: 0:11:34 ETA: 00:00:00
=== Performance result === Accuracy: 83.45947973986993 (+/-) 2.058268000782759 Testing Loss: 0.34304751650341275 (+/-) 0.03419052307359971 Precision: 0.8360104606664316 Recall: 0.8345947973986994 F1 score: 0.8344192697590035 Testing Time: 0.012422821293955388 (+/-) 0.009739921809315082 Training Time: 0.3177014010259066 (+/-) 0.011728058077953294 === Average network evolution === Total hidden node: 6.057028514257128 (+/-) 0.37791637313019877 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=28, out_features=6, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=6, out_features=2, bias=True) ) No. of inputs : 28 No. of nodes : 6 No. of parameters : 188 Voting weight: [1.0]
100% (2000 of 2000) |####################| Elapsed Time: 0:11:33 ETA: 00:00:00
=== Performance result === Accuracy: 83.47888944472236 (+/-) 1.9273042879090831 Testing Loss: 0.34332850324982345 (+/-) 0.033716106381026636 Precision: 0.8361366096093388 Recall: 0.8347888944472236 F1 score: 0.83462203232571 Testing Time: 0.012395198849691876 (+/-) 0.009754258265551258 Training Time: 0.3173999484626575 (+/-) 0.010827725003493825 === Average network evolution === Total hidden node: 5.451225612806403 (+/-) 0.6439756213745785 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=28, out_features=6, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=6, out_features=2, bias=True) ) No. of inputs : 28 No. of nodes : 6 No. of parameters : 188 Voting weight: [1.0]
100% (2000 of 2000) |####################| Elapsed Time: 0:11:36 ETA: 00:00:00
=== Performance result === Accuracy: 83.59564782391196 (+/-) 1.8260622442003076 Testing Loss: 0.34211599780596036 (+/-) 0.03224146237329054 Precision: 0.8371641530996696 Recall: 0.8359564782391196 F1 score: 0.8358084251905796 Testing Time: 0.012672097042478759 (+/-) 0.009787881220249775 Training Time: 0.3187490265747498 (+/-) 0.011403259355202117 === Average network evolution === Total hidden node: 7.298149074537268 (+/-) 0.6887588621375267 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=28, out_features=8, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=8, out_features=2, bias=True) ) No. of inputs : 28 No. of nodes : 8 No. of parameters : 250 Voting weight: [1.0]
100% (2000 of 2000) |####################| Elapsed Time: 0:11:32 ETA: 00:00:00
=== Performance result === Accuracy: 83.43611805902951 (+/-) 2.0220164226028614 Testing Loss: 0.34529156803249894 (+/-) 0.03487135493302157 Precision: 0.8357031982977841 Recall: 0.8343611805902952 F1 score: 0.8341943766696143 Testing Time: 0.012286856390345746 (+/-) 0.009762856871547617 Training Time: 0.31696684053983015 (+/-) 0.012024711638206051 === Average network evolution === Total hidden node: 3.5802901450725364 (+/-) 0.7627073994308055 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=28, out_features=3, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=3, out_features=2, bias=True) ) No. of inputs : 28 No. of nodes : 3 No. of parameters : 95 Voting weight: [1.0]
Mean Accuracy: 83.48228228228228 Std Accuracy: 1.9513093051591788 Hidden Node mean 5.686686686686687 Hidden Node std: 1.359772743824416 Hidden Layer mean: 1.0 Hidden Layer std: 0.0 Infinite Delay
100% (2000 of 2000) |####################| Elapsed Time: 0:00:54 ETA: 00:00:00
=== Performance result === Accuracy: 62.67798899449725 (+/-) 1.554684623973283 Testing Loss: 0.6374242153389564 (+/-) 0.005525817776874546 Precision: 0.7458737036753178 Recall: 0.6267798899449725 F1 score: 0.5753196222594495 Testing Time: 0.011182063337920486 (+/-) 0.00939307221528819 Training Time: 4.990211780695035e-07 (+/-) 2.2305744283736114e-05 === Average network evolution === Total hidden node: 5.0 (+/-) 0.0 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=28, out_features=5, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=5, out_features=2, bias=True) ) No. of inputs : 28 No. of nodes : 5 No. of parameters : 157 Voting weight: [1.0]
100% (2000 of 2000) |####################| Elapsed Time: 0:00:54 ETA: 00:00:00
=== Performance result === Accuracy: 56.17548774387194 (+/-) 1.5931096788825736 Testing Loss: 0.6556168000599096 (+/-) 0.006513087733077176 Precision: 0.7047826874158696 Recall: 0.5617548774387193 F1 score: 0.46897538865666893 Testing Time: 0.011050442447061238 (+/-) 0.009357753169711542 Training Time: 9.970882047469047e-07 (+/-) 3.150704426316052e-05 === Average network evolution === Total hidden node: 4.0 (+/-) 0.0 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=28, out_features=4, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=4, out_features=2, bias=True) ) No. of inputs : 28 No. of nodes : 4 No. of parameters : 126 Voting weight: [1.0]
100% (2000 of 2000) |####################| Elapsed Time: 0:00:54 ETA: 00:00:00
=== Performance result === Accuracy: 65.69854927463732 (+/-) 1.4930999866831898 Testing Loss: 0.6667438975687681 (+/-) 0.00221969986519877 Precision: 0.6630181515004179 Recall: 0.6569854927463732 F1 score: 0.6537710090092951 Testing Time: 0.011396741914772999 (+/-) 0.009379764271877703 Training Time: 4.986633712974652e-07 (+/-) 2.228975068123822e-05 === Average network evolution === Total hidden node: 6.0 (+/-) 0.0 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=28, out_features=6, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=6, out_features=2, bias=True) ) No. of inputs : 28 No. of nodes : 6 No. of parameters : 188 Voting weight: [1.0]
100% (2000 of 2000) |####################| Elapsed Time: 0:00:54 ETA: 00:00:00
=== Performance result === Accuracy: 53.372236118059035 (+/-) 1.6041699513744123 Testing Loss: 0.6844265985154938 (+/-) 0.00215083355586622 Precision: 0.6606683126636556 Recall: 0.5337223611805902 F1 score: 0.41884784834218325 Testing Time: 0.011092239764405824 (+/-) 0.009422762600552966 Training Time: 4.98782640221478e-07 (+/-) 2.229508188207085e-05 === Average network evolution === Total hidden node: 4.0 (+/-) 0.0 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=28, out_features=4, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=4, out_features=2, bias=True) ) No. of inputs : 28 No. of nodes : 4 No. of parameters : 126 Voting weight: [1.0]
100% (2000 of 2000) |####################| Elapsed Time: 0:00:54 ETA: 00:00:00
=== Performance result === Accuracy: 50.6855927963982 (+/-) 1.603015085690278 Testing Loss: 0.6937006667532165 (+/-) 0.002769225790506218 Precision: 0.5207578114713997 Recall: 0.506855927963982 F1 score: 0.40828839629165037 Testing Time: 0.010954023302048668 (+/-) 0.009276656812183365 Training Time: 2.493793932183377e-06 (+/-) 4.980101514031178e-05 === Average network evolution === Total hidden node: 4.0 (+/-) 0.0 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=28, out_features=4, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=4, out_features=2, bias=True) ) No. of inputs : 28 No. of nodes : 4 No. of parameters : 126 Voting weight: [1.0]
Mean Accuracy: 57.72203203203203 Std Accuracy: 5.853774744020195 Hidden Node mean 4.6 Hidden Node std: 0.7999999999999999 Hidden Layer mean: 1.0 Hidden Layer std: 0.0
In [8]:
%run ADL_susy.ipynb
Number of input: 18 Number of output: 2 Number of batch: 2000 All labeled
100% (2000 of 2000) |####################| Elapsed Time: 0:42:55 ETA: 00:00:00
=== Performance result === Accuracy: 78.00530265132566 (+/-) 2.5477926759663605 Testing Loss: 0.46744417576207825 (+/-) 0.034255557328922166 Precision: 0.7822284144624688 Recall: 0.7800530265132566 F1 score: 0.7779677322139856 Testing Time: 0.013515181157396935 (+/-) 0.01008145384030837 Training Time: 1.2577700285746969 (+/-) 0.02352862081228845 === Average network evolution === Total hidden node: 11.813906953476739 (+/-) 1.9604357544996043 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=18, out_features=13, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=13, out_features=2, bias=True) ) No. of inputs : 18 No. of nodes : 13 No. of parameters : 275 Voting weight: [1.0]
100% (2000 of 2000) |####################| Elapsed Time: 0:42:42 ETA: 00:00:00
=== Performance result === Accuracy: 78.05737868934467 (+/-) 2.672716977194962 Testing Loss: 0.46626426806564386 (+/-) 0.035204229603081366 Precision: 0.7825970670241548 Recall: 0.7805737868934467 F1 score: 0.7785662035835066 Testing Time: 0.014359636387865563 (+/-) 0.009999732500537532 Training Time: 1.2501758929191082 (+/-) 0.02367805899284882 === Average network evolution === Total hidden node: 21.51225612806403 (+/-) 2.870512982869722 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=18, out_features=24, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=24, out_features=2, bias=True) ) No. of inputs : 18 No. of nodes : 24 No. of parameters : 506 Voting weight: [1.0]
100% (2000 of 2000) |####################| Elapsed Time: 0:42:37 ETA: 00:00:00
=== Performance result === Accuracy: 77.87058529264631 (+/-) 2.867182515186555 Testing Loss: 0.4692309184066053 (+/-) 0.036828362257350214 Precision: 0.7807690216589541 Recall: 0.7787058529264632 F1 score: 0.7766410442188558 Testing Time: 0.013383330435321115 (+/-) 0.010024050849534581 Training Time: 1.2483128497098432 (+/-) 0.022542728630977116 === Average network evolution === Total hidden node: 10.665332666333166 (+/-) 2.5922796403465656 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=18, out_features=13, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=13, out_features=2, bias=True) ) No. of inputs : 18 No. of nodes : 13 No. of parameters : 275 Voting weight: [1.0]
100% (2000 of 2000) |####################| Elapsed Time: 0:42:33 ETA: 00:00:00
=== Performance result === Accuracy: 77.84502251125564 (+/-) 2.763022101352028 Testing Loss: 0.47003147539763285 (+/-) 0.0352543797824029 Precision: 0.7804174607789107 Recall: 0.7784502251125562 F1 score: 0.776423046312149 Testing Time: 0.013292218518889266 (+/-) 0.009987069496005542 Training Time: 1.2468084819081904 (+/-) 0.022622585632566555 === Average network evolution === Total hidden node: 9.948474237118559 (+/-) 2.340637886574863 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=18, out_features=11, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=11, out_features=2, bias=True) ) No. of inputs : 18 No. of nodes : 11 No. of parameters : 233 Voting weight: [1.0]
100% (2000 of 2000) |####################| Elapsed Time: 0:42:41 ETA: 00:00:00
=== Performance result === Accuracy: 78.0760380190095 (+/-) 2.6494699386921328 Testing Loss: 0.4657830270216905 (+/-) 0.034402998354037456 Precision: 0.7827786394929879 Recall: 0.7807603801900951 F1 score: 0.7787589037511858 Testing Time: 0.014197529286608331 (+/-) 0.01040309580456962 Training Time: 1.2499625205755114 (+/-) 0.02104379380197161 === Average network evolution === Total hidden node: 17.43271635817909 (+/-) 3.2872105274249397 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=18, out_features=20, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=20, out_features=2, bias=True) ) No. of inputs : 18 No. of nodes : 20 No. of parameters : 422 Voting weight: [1.0]
Mean Accuracy: 77.98137137137137 Std Accuracy: 2.6633034950466965 Hidden Node mean 14.277977977977978 Hidden Node std: 5.199032164832843 Hidden Layer mean: 1.0 Hidden Layer std: 0.0 50% labeled
100% (2000 of 2000) |####################| Elapsed Time: 0:23:57 ETA: 00:00:00
=== Performance result === Accuracy: 76.76538269134566 (+/-) 3.7641063334296554 Testing Loss: 0.48676223821077064 (+/-) 0.045639399700106255 Precision: 0.7697171673423313 Recall: 0.7676538269134567 F1 score: 0.7653370657795279 Testing Time: 0.012887020716970118 (+/-) 0.010670375093770511 Training Time: 0.6879102717404845 (+/-) 0.0836781463421194 === Average network evolution === Total hidden node: 8.652326163081542 (+/-) 2.9044623069196462 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=18, out_features=12, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=12, out_features=2, bias=True) ) No. of inputs : 18 No. of nodes : 12 No. of parameters : 254 Voting weight: [1.0]
100% (2000 of 2000) |####################| Elapsed Time: 0:23:55 ETA: 00:00:00
=== Performance result === Accuracy: 77.15952976488242 (+/-) 3.3292070811056402 Testing Loss: 0.48024906716745097 (+/-) 0.04059501339373892 Precision: 0.7740878013303962 Recall: 0.7715952976488244 F1 score: 0.7691746374063072 Testing Time: 0.011883897862474938 (+/-) 0.009774998558244477 Training Time: 0.6894916786796871 (+/-) 0.07810592362584406 === Average network evolution === Total hidden node: 9.481240620310155 (+/-) 1.8727725169066465 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=18, out_features=12, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=12, out_features=2, bias=True) ) No. of inputs : 18 No. of nodes : 12 No. of parameters : 254 Voting weight: [1.0]
100% (2000 of 2000) |####################| Elapsed Time: 0:21:42 ETA: 00:00:00
=== Performance result === Accuracy: 77.06263131565784 (+/-) 3.2354510274945403 Testing Loss: 0.4820119719943027 (+/-) 0.041847091377951305 Precision: 0.7735225894718236 Recall: 0.7706263131565783 F1 score: 0.7680024828487249 Testing Time: 0.011178442333387459 (+/-) 0.008709680858879245 Training Time: 0.6242773209648648 (+/-) 0.014298204341692102 === Average network evolution === Total hidden node: 10.174587293646823 (+/-) 1.9659519324640187 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=18, out_features=13, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=13, out_features=2, bias=True) ) No. of inputs : 18 No. of nodes : 13 No. of parameters : 275 Voting weight: [1.0]
100% (2000 of 2000) |####################| Elapsed Time: 0:21:44 ETA: 00:00:00
=== Performance result === Accuracy: 77.18369184592297 (+/-) 3.1387354152734965 Testing Loss: 0.48067665602518 (+/-) 0.038927147076005336 Precision: 0.774053050889269 Recall: 0.7718369184592296 F1 score: 0.769547908084622 Testing Time: 0.01121166946292818 (+/-) 0.008992896111568751 Training Time: 0.6252112841832751 (+/-) 0.014864281890515868 === Average network evolution === Total hidden node: 10.02751375687844 (+/-) 1.9497805501601284 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=18, out_features=12, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=12, out_features=2, bias=True) ) No. of inputs : 18 No. of nodes : 12 No. of parameters : 254 Voting weight: [1.0]
100% (2000 of 2000) |####################| Elapsed Time: 0:23:31 ETA: 00:00:00
=== Performance result === Accuracy: 77.2176088044022 (+/-) 3.183987904268762 Testing Loss: 0.48033550973532496 (+/-) 0.041124696730940685 Precision: 0.7738405695960491 Recall: 0.772176088044022 F1 score: 0.7701582499174392 Testing Time: 0.012538481259596473 (+/-) 0.0100371965408198 Training Time: 0.676326369213545 (+/-) 0.04866747894628626 === Average network evolution === Total hidden node: 13.534767383691847 (+/-) 3.1720179195991056 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=18, out_features=17, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=17, out_features=2, bias=True) ) No. of inputs : 18 No. of nodes : 17 No. of parameters : 359 Voting weight: [1.0]
Mean Accuracy: 77.08850850850851 Std Accuracy: 3.3081414536798803 Hidden Node mean 10.376376376376376 Hidden Node std: 2.9510322047642985 Hidden Layer mean: 1.0 Hidden Layer std: 0.0 25% labeled
100% (2000 of 2000) |####################| Elapsed Time: 0:12:28 ETA: 00:00:00
=== Performance result === Accuracy: 75.10130065032516 (+/-) 5.294356751850267 Testing Loss: 0.5085699502499834 (+/-) 0.05720700284730417 Precision: 0.7540093993470135 Recall: 0.7510130065032516 F1 score: 0.7477619134411412 Testing Time: 0.011712452720081049 (+/-) 0.009883049287556995 Training Time: 0.34588963321115207 (+/-) 0.02586675338198594 === Average network evolution === Total hidden node: 5.655827913956979 (+/-) 2.482072751748765 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=18, out_features=9, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=9, out_features=2, bias=True) ) No. of inputs : 18 No. of nodes : 9 No. of parameters : 191 Voting weight: [1.0]
100% (2000 of 2000) |####################| Elapsed Time: 0:13:39 ETA: 00:00:00
=== Performance result === Accuracy: 75.80280140070036 (+/-) 4.31407902048346 Testing Loss: 0.49924272500079175 (+/-) 0.0502419985237688 Precision: 0.7607987265839188 Recall: 0.7580280140070035 F1 score: 0.7551089420243012 Testing Time: 0.01314068198382944 (+/-) 0.010657177879193675 Training Time: 0.37847294325587627 (+/-) 0.014704150658411318 === Average network evolution === Total hidden node: 7.147073536768384 (+/-) 2.071358359343322 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=18, out_features=10, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=10, out_features=2, bias=True) ) No. of inputs : 18 No. of nodes : 10 No. of parameters : 212 Voting weight: [1.0]
100% (2000 of 2000) |####################| Elapsed Time: 0:13:42 ETA: 00:00:00
=== Performance result === Accuracy: 74.736168084042 (+/-) 4.6052526206074385 Testing Loss: 0.515989195143598 (+/-) 0.05201111393000463 Precision: 0.7509023779895042 Recall: 0.7473616808404202 F1 score: 0.7437112976340987 Testing Time: 0.011321809901303801 (+/-) 0.009302504688498208 Training Time: 0.38179562615417967 (+/-) 0.010217282260838248 === Average network evolution === Total hidden node: 2.7933966983491745 (+/-) 0.5069170550094307 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=18, out_features=3, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=3, out_features=2, bias=True) ) No. of inputs : 18 No. of nodes : 3 No. of parameters : 65 Voting weight: [1.0]
100% (2000 of 2000) |####################| Elapsed Time: 0:13:45 ETA: 00:00:00
=== Performance result === Accuracy: 75.81770885442721 (+/-) 4.253482409694606 Testing Loss: 0.5000724779957232 (+/-) 0.04845101695909449 Precision: 0.7604699262560428 Recall: 0.7581770885442721 F1 score: 0.7554997650397659 Testing Time: 0.013061831986206422 (+/-) 0.010621359395612604 Training Time: 0.38141021769067057 (+/-) 0.010512446313708757 === Average network evolution === Total hidden node: 6.164582291145573 (+/-) 2.087966957620405 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=18, out_features=9, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=9, out_features=2, bias=True) ) No. of inputs : 18 No. of nodes : 9 No. of parameters : 191 Voting weight: [1.0]
100% (2000 of 2000) |####################| Elapsed Time: 0:13:39 ETA: 00:00:00
=== Performance result === Accuracy: 76.08409204602302 (+/-) 3.7165620511800825 Testing Loss: 0.49623057787390934 (+/-) 0.046188077879307524 Precision: 0.7635387885174375 Recall: 0.7608409204602301 F1 score: 0.7580390376670408 Testing Time: 0.013489275827832435 (+/-) 0.010735151251004094 Training Time: 0.37790738659658807 (+/-) 0.009398113618371205 === Average network evolution === Total hidden node: 10.576788394197099 (+/-) 2.219784947546056 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=18, out_features=14, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=14, out_features=2, bias=True) ) No. of inputs : 18 No. of nodes : 14 No. of parameters : 296 Voting weight: [1.0]
Mean Accuracy: 75.51875875875876 Std Accuracy: 4.472293132915998 Hidden Node mean 6.468668668668669 Hidden Node std: 3.2124895982318877 Hidden Layer mean: 1.0 Hidden Layer std: 0.0 Infinite Delay
99% (1999 of 2000) |################### | Elapsed Time: 0:00:59 ETA: 0:00:00
=== Performance result === Accuracy: 51.704102051025515 (+/-) 1.5705720390531992 Testing Loss: 0.691420068229181 (+/-) 0.0017208317438658863 Precision: 0.5682315454056828 Recall: 0.5170410205102551 F1 score: 0.4757090417128868 Testing Time: 0.012343252820334117 (+/-) 0.010820442847535144 Training Time: 9.91840372090342e-07 (+/-) 3.1341736724551546e-05 === Average network evolution === Total hidden node: 5.0 (+/-) 0.0 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=18, out_features=5, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=5, out_features=2, bias=True) ) No. of inputs : 18 No. of nodes : 5 No. of parameters : 107 Voting weight: [1.0]
100% (2000 of 2000) |####################| Elapsed Time: 0:00:59 ETA: 00:00:00
=== Performance result === Accuracy: 61.60035017508755 (+/-) 1.510117579856355 Testing Loss: 0.6820684604909553 (+/-) 0.0014671437301067359 Precision: 0.6441095627165845 Recall: 0.6160035017508755 F1 score: 0.5728519118628765 Testing Time: 0.012120761532614146 (+/-) 0.010620884366524311 Training Time: 1.5048160142693417e-06 (+/-) 3.881664672769537e-05 === Average network evolution === Total hidden node: 4.0 (+/-) 0.0 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=18, out_features=4, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=4, out_features=2, bias=True) ) No. of inputs : 18 No. of nodes : 4 No. of parameters : 86 Voting weight: [1.0]
100% (2000 of 2000) |####################| Elapsed Time: 0:00:59 ETA: 00:00:00
=== Performance result === Accuracy: 54.66093046523262 (+/-) 1.5733871450540848 Testing Loss: 0.6883744914988508 (+/-) 0.0025939343100569497 Precision: 0.5859419653270574 Recall: 0.5466093046523262 F1 score: 0.4005888579984073 Testing Time: 0.01207279741555348 (+/-) 0.010314057036444089 Training Time: 4.980670266774012e-07 (+/-) 2.2263094677075055e-05 === Average network evolution === Total hidden node: 3.0 (+/-) 0.0 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=18, out_features=3, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=3, out_features=2, bias=True) ) No. of inputs : 18 No. of nodes : 3 No. of parameters : 65 Voting weight: [1.0]
100% (2000 of 2000) |####################| Elapsed Time: 0:01:00 ETA: 00:00:00
=== Performance result === Accuracy: 54.23906953476739 (+/-) 1.5656643916117252 Testing Loss: 0.6898041681804438 (+/-) 0.004756907121193263 Precision: 0.7517972853190777 Recall: 0.5423906953476738 F1 score: 0.38147134384025033 Testing Time: 0.01216755717202626 (+/-) 0.010738612511248037 Training Time: 2.496417848511658e-06 (+/-) 4.9853420957717e-05 === Average network evolution === Total hidden node: 3.0 (+/-) 0.0 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=18, out_features=3, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=3, out_features=2, bias=True) ) No. of inputs : 18 No. of nodes : 3 No. of parameters : 65 Voting weight: [1.0]
100% (2000 of 2000) |####################| Elapsed Time: 0:00:59 ETA: 00:00:00
=== Performance result === Accuracy: 49.4816408204102 (+/-) 1.6060379160992748 Testing Loss: 0.7006591322303951 (+/-) 0.003000627388455331 Precision: 0.5123545696479324 Recall: 0.49481640820410205 F1 score: 0.4838415832199744 Testing Time: 0.012373345204745012 (+/-) 0.01058769446706073 Training Time: 1.9963232501260395e-06 (+/-) 4.458332414952005e-05 === Average network evolution === Total hidden node: 5.0 (+/-) 0.0 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=18, out_features=5, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=5, out_features=2, bias=True) ) No. of inputs : 18 No. of nodes : 5 No. of parameters : 107 Voting weight: [1.0]
Mean Accuracy: 54.33674674674675 Std Accuracy: 4.372474191745951 Hidden Node mean 4.0 Hidden Node std: 0.8944271909999159 Hidden Layer mean: 1.0 Hidden Layer std: 0.0
In [9]:
%run ADL_electricitypricing.ipynb
Number of input: 8 Number of output: 2 Number of batch: 45 All labeled
100% (45 of 45) |########################| Elapsed Time: 0:01:44 ETA: 00:00:00
=== Performance result === Accuracy: 57.81363636363638 (+/-) 7.3946415153471685 Testing Loss: 0.6708605275912718 (+/-) 0.02272830281356067 Precision: 0.5520166250533703 Recall: 0.5781363636363637 F1 score: 0.505815291734194 Testing Time: 0.010455792600458319 (+/-) 0.013123078416592156 Training Time: 2.366582301529971 (+/-) 0.7818014347170686 === Average network evolution === Total hidden node: 14.704545454545455 (+/-) 5.3664765207661045 Number of layer: 3.409090909090909 (+/-) 1.2120265114521258 === Final network structure === basicNet( (linear): Linear(in_features=8, out_features=3, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=3, out_features=2, bias=True) ) No. of inputs : 8 No. of nodes : 3 No. of parameters : 35 basicNet( (linear): Linear(in_features=3, out_features=5, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=5, out_features=2, bias=True) ) No. of inputs : 3 No. of nodes : 5 No. of parameters : 32 basicNet( (linear): Linear(in_features=5, out_features=4, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=4, out_features=2, bias=True) ) No. of inputs : 5 No. of nodes : 4 No. of parameters : 34 basicNet( (linear): Linear(in_features=4, out_features=5, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=5, out_features=2, bias=True) ) No. of inputs : 4 No. of nodes : 5 No. of parameters : 37 basicNet( (linear): Linear(in_features=5, out_features=5, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=5, out_features=2, bias=True) ) No. of inputs : 5 No. of nodes : 5 No. of parameters : 42 Voting weight: [0.0, 0.4997183008050181, 0.0, 0.0005633983899638098, 0.4997183008050181]
100% (45 of 45) |########################| Elapsed Time: 0:01:12 ETA: 00:00:00
=== Performance result === Accuracy: 61.575 (+/-) 8.036822217993649 Testing Loss: 0.6335059851408005 (+/-) 0.048896460520388214 Precision: 0.6063829287763294 Recall: 0.61575 F1 score: 0.5996802904492604 Testing Time: 0.005687800320712003 (+/-) 0.009406490600081889 Training Time: 1.6436270150271328 (+/-) 0.30126986238035397 === Average network evolution === Total hidden node: 5.931818181818182 (+/-) 3.557308272944634 Number of layer: 1.2954545454545454 (+/-) 0.6244832574560949 === Final network structure === basicNet( (linear): Linear(in_features=8, out_features=4, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=4, out_features=2, bias=True) ) No. of inputs : 8 No. of nodes : 4 No. of parameters : 46 Voting weight: [1.0]
100% (45 of 45) |########################| Elapsed Time: 0:01:08 ETA: 00:00:00
=== Performance result === Accuracy: 65.56136363636364 (+/-) 6.5602181196100116 Testing Loss: 0.6132604879411784 (+/-) 0.05731778206984663 Precision: 0.6505456957294925 Recall: 0.6556136363636363 F1 score: 0.6489131586779373 Testing Time: 0.00440128283067183 (+/-) 0.007439060744968732 Training Time: 1.5523505861108953 (+/-) 0.1018618025738576 === Average network evolution === Total hidden node: 7.795454545454546 (+/-) 1.531184114791043 Number of layer: 1.0454545454545454 (+/-) 0.20829889522526546 === Final network structure === basicNet( (linear): Linear(in_features=8, out_features=9, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=9, out_features=2, bias=True) ) No. of inputs : 8 No. of nodes : 9 No. of parameters : 101 Voting weight: [1.0]
100% (45 of 45) |########################| Elapsed Time: 0:01:18 ETA: 00:00:00
=== Performance result === Accuracy: 64.81136363636364 (+/-) 7.0479595986450025 Testing Loss: 0.6253216090527448 (+/-) 0.05958365567573209 Precision: 0.6425676907879293 Recall: 0.6481136363636364 F1 score: 0.636075702408277 Testing Time: 0.005960041826421564 (+/-) 0.009806372427248649 Training Time: 1.784017730842937 (+/-) 0.37014210524735786 === Average network evolution === Total hidden node: 9.909090909090908 (+/-) 3.308516433650517 Number of layer: 1.3863636363636365 (+/-) 0.5727092349251888 === Final network structure === basicNet( (linear): Linear(in_features=8, out_features=9, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=9, out_features=2, bias=True) ) No. of inputs : 8 No. of nodes : 9 No. of parameters : 101 basicNet( (linear): Linear(in_features=9, out_features=5, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=5, out_features=2, bias=True) ) No. of inputs : 9 No. of nodes : 5 No. of parameters : 62 Voting weight: [0.0, 1.0]
100% (45 of 45) |########################| Elapsed Time: 0:01:15 ETA: 00:00:00
=== Performance result === Accuracy: 63.974999999999994 (+/-) 8.35624766267731 Testing Loss: 0.6322945749217813 (+/-) 0.0612951913603268 Precision: 0.6371678689361756 Recall: 0.63975 F1 score: 0.6380503117442345 Testing Time: 0.005734107711098411 (+/-) 0.009076347679689857 Training Time: 1.7151612531055103 (+/-) 0.4380454872671639 === Average network evolution === Total hidden node: 11.090909090909092 (+/-) 4.851514205136849 Number of layer: 1.2954545454545454 (+/-) 0.45624681590647115 === Final network structure === basicNet( (linear): Linear(in_features=8, out_features=10, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=10, out_features=2, bias=True) ) No. of inputs : 8 No. of nodes : 10 No. of parameters : 112 basicNet( (linear): Linear(in_features=10, out_features=9, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=9, out_features=2, bias=True) ) No. of inputs : 10 No. of nodes : 9 No. of parameters : 119 Voting weight: [0.0, 1.0]
Mean Accuracy: 63.103720930232555 Std Accuracy: 7.1020393478820045 Hidden Node mean 9.944186046511629 Hidden Node std: 4.988046284150594 Hidden Layer mean: 1.697674418604651 Hidden Layer std: 1.123426728775396 50% labeled
100% (45 of 45) |########################| Elapsed Time: 0:00:34 ETA: 00:00:00
=== Performance result === Accuracy: 63.697727272727256 (+/-) 6.784122125708596 Testing Loss: 0.6220933916893873 (+/-) 0.04814847695145634 Precision: 0.6306950526161613 Recall: 0.6369772727272728 F1 score: 0.6291974124956567 Testing Time: 0.0042202364314686165 (+/-) 0.007456163710133397 Training Time: 0.7865779020569541 (+/-) 0.042849104631892634 === Average network evolution === Total hidden node: 5.545454545454546 (+/-) 0.49792959773196915 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=8, out_features=6, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=6, out_features=2, bias=True) ) No. of inputs : 8 No. of nodes : 6 No. of parameters : 68 Voting weight: [1.0]
100% (45 of 45) |########################| Elapsed Time: 0:00:33 ETA: 00:00:00
=== Performance result === Accuracy: 62.92954545454545 (+/-) 6.762919607061009 Testing Loss: 0.6311250478029251 (+/-) 0.06769831661317884 Precision: 0.6217311865134764 Recall: 0.6292954545454545 F1 score: 0.6146636840004508 Testing Time: 0.003327608108520508 (+/-) 0.0010340437788820362 Training Time: 0.7618599425662648 (+/-) 0.012053577899492112 === Average network evolution === Total hidden node: 7.4772727272727275 (+/-) 1.0763709305649654 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=8, out_features=9, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=9, out_features=2, bias=True) ) No. of inputs : 8 No. of nodes : 9 No. of parameters : 101 Voting weight: [1.0]
100% (45 of 45) |########################| Elapsed Time: 0:00:33 ETA: 00:00:00
=== Performance result === Accuracy: 60.718181818181826 (+/-) 7.073711663208706 Testing Loss: 0.6457081450657411 (+/-) 0.04940393068538957 Precision: 0.5976560204974379 Recall: 0.6071818181818182 F1 score: 0.5951018902682981 Testing Time: 0.0042848370291969995 (+/-) 0.006391291635861934 Training Time: 0.7617661682042208 (+/-) 0.014046577005405443 === Average network evolution === Total hidden node: 8.931818181818182 (+/-) 0.6535819929340183 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=8, out_features=10, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=10, out_features=2, bias=True) ) No. of inputs : 8 No. of nodes : 10 No. of parameters : 112 Voting weight: [1.0]
100% (45 of 45) |########################| Elapsed Time: 0:00:33 ETA: 00:00:00
=== Performance result === Accuracy: 61.43181818181818 (+/-) 7.973643308005808 Testing Loss: 0.6310233514417302 (+/-) 0.04674968508080527 Precision: 0.6050271115105956 Recall: 0.6143181818181818 F1 score: 0.6003147269634336 Testing Time: 0.004425997083837336 (+/-) 0.00699895799099366 Training Time: 0.760376209562475 (+/-) 0.01544847042940078 === Average network evolution === Total hidden node: 8.568181818181818 (+/-) 0.6178307826849176 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=8, out_features=8, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=8, out_features=2, bias=True) ) No. of inputs : 8 No. of nodes : 8 No. of parameters : 90 Voting weight: [1.0]
100% (45 of 45) |########################| Elapsed Time: 0:00:33 ETA: 00:00:00
=== Performance result === Accuracy: 59.19772727272728 (+/-) 7.911800411019078 Testing Loss: 0.6503746482458982 (+/-) 0.04174595097621097 Precision: 0.585419452209386 Recall: 0.5919772727272727 F1 score: 0.5867451992902079 Testing Time: 0.003964781761169434 (+/-) 0.006735531375566166 Training Time: 0.7651583335616372 (+/-) 0.011387877545221258 === Average network evolution === Total hidden node: 3.022727272727273 (+/-) 0.14903269373413636 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=8, out_features=3, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=3, out_features=2, bias=True) ) No. of inputs : 8 No. of nodes : 3 No. of parameters : 35 Voting weight: [1.0]
Mean Accuracy: 61.996744186046506 Std Accuracy: 6.597556884297092 Hidden Node mean 6.702325581395349 Hidden Node std: 2.2792785855925866 Hidden Layer mean: 1.0 Hidden Layer std: 0.0 25% labeled
100% (45 of 45) |########################| Elapsed Time: 0:00:16 ETA: 00:00:00
=== Performance result === Accuracy: 60.25454545454545 (+/-) 6.347027025790556 Testing Loss: 0.6448589360172098 (+/-) 0.03462017714248512 Precision: 0.5923980947382137 Recall: 0.6025454545454545 F1 score: 0.5897662554304925 Testing Time: 0.004529812119223855 (+/-) 0.0068081151606404515 Training Time: 0.3800530433654785 (+/-) 0.00865523089244446 === Average network evolution === Total hidden node: 8.590909090909092 (+/-) 0.49166608301781667 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=8, out_features=9, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=9, out_features=2, bias=True) ) No. of inputs : 8 No. of nodes : 9 No. of parameters : 101 Voting weight: [1.0]
100% (45 of 45) |########################| Elapsed Time: 0:00:16 ETA: 00:00:00
=== Performance result === Accuracy: 57.59318181818182 (+/-) 7.641049360564195 Testing Loss: 0.6761251213875684 (+/-) 0.02975795432012827 Precision: 0.5538258765893176 Recall: 0.5759318181818182 F1 score: 0.5354556290635968 Testing Time: 0.0040433569387956095 (+/-) 0.007481319705674717 Training Time: 0.37956480004570703 (+/-) 0.0077733260298382635 === Average network evolution === Total hidden node: 3.8181818181818183 (+/-) 0.4406981688560299 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=8, out_features=3, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=3, out_features=2, bias=True) ) No. of inputs : 8 No. of nodes : 3 No. of parameters : 35 Voting weight: [1.0]
100% (45 of 45) |########################| Elapsed Time: 0:00:16 ETA: 00:00:00
=== Performance result === Accuracy: 59.60454545454545 (+/-) 6.71930578616079 Testing Loss: 0.6570572880181399 (+/-) 0.039321139719617114 Precision: 0.5853152088240164 Recall: 0.5960454545454545 F1 score: 0.5832134726625113 Testing Time: 0.004290976307608865 (+/-) 0.006530079787262215 Training Time: 0.38010282949967816 (+/-) 0.006634936974227754 === Average network evolution === Total hidden node: 7.545454545454546 (+/-) 0.49792959773196915 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=8, out_features=8, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=8, out_features=2, bias=True) ) No. of inputs : 8 No. of nodes : 8 No. of parameters : 90 Voting weight: [1.0]
100% (45 of 45) |########################| Elapsed Time: 0:00:16 ETA: 00:00:00
=== Performance result === Accuracy: 59.6340909090909 (+/-) 6.503004312057977 Testing Loss: 0.660595337098295 (+/-) 0.04019124638781493 Precision: 0.5886636282038722 Recall: 0.5963409090909091 F1 score: 0.5894541064041388 Testing Time: 0.003903665325858376 (+/-) 0.006740014172392363 Training Time: 0.3804617632519115 (+/-) 0.011941400396377564 === Average network evolution === Total hidden node: 6.7272727272727275 (+/-) 0.4453617714151233 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=8, out_features=7, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=7, out_features=2, bias=True) ) No. of inputs : 8 No. of nodes : 7 No. of parameters : 79 Voting weight: [1.0]
100% (45 of 45) |########################| Elapsed Time: 0:00:16 ETA: 00:00:00
=== Performance result === Accuracy: 59.852272727272705 (+/-) 5.973596778413686 Testing Loss: 0.6614910133860328 (+/-) 0.03047099591487847 Precision: 0.5854382336772438 Recall: 0.5985227272727273 F1 score: 0.5608488456286037 Testing Time: 0.003682320768182928 (+/-) 0.007062555192163006 Training Time: 0.37675414843992755 (+/-) 0.007640665476902541 === Average network evolution === Total hidden node: 4.5227272727272725 (+/-) 0.4994832039962707 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=8, out_features=4, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=4, out_features=2, bias=True) ) No. of inputs : 8 No. of nodes : 4 No. of parameters : 46 Voting weight: [1.0]
Mean Accuracy: 59.69395348837209 Std Accuracy: 6.199505659037769 Hidden Node mean 6.232558139534884 Hidden Node std: 1.8731544008464684 Hidden Layer mean: 1.0 Hidden Layer std: 0.0 Infinite Delay
73% (33 of 45) |################# | Elapsed Time: 0:00:00 ETA: 0:00:00
=== Performance result === Accuracy: 56.37954545454546 (+/-) 7.929048422370589 Testing Loss: 0.6843312951651487 (+/-) 0.016688533590044623 Precision: 0.6141323223394426 Recall: 0.5637954545454545 F1 score: 0.5558617184048541 Testing Time: 0.003253053535114635 (+/-) 0.0065461513409619315 Training Time: 0.0 (+/-) 0.0 === Average network evolution === Total hidden node: 6.0 (+/-) 0.0 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=8, out_features=6, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=6, out_features=2, bias=True) ) No. of inputs : 8 No. of nodes : 6 No. of parameters : 68 Voting weight: [1.0]
77% (35 of 45) |################## | Elapsed Time: 0:00:00 ETA: 0:00:00
=== Performance result === Accuracy: 58.37272727272728 (+/-) 6.113932064494683 Testing Loss: 0.6735491508787329 (+/-) 0.02473988698809039 Precision: 0.5667684036616671 Recall: 0.5837272727272728 F1 score: 0.4882857918450825 Testing Time: 0.0030154856768521395 (+/-) 0.006419616267122874 Training Time: 0.0 (+/-) 0.0 === Average network evolution === Total hidden node: 4.0 (+/-) 0.0 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=8, out_features=4, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=4, out_features=2, bias=True) ) No. of inputs : 8 No. of nodes : 4 No. of parameters : 46 Voting weight: [1.0]
97% (44 of 45) |####################### | Elapsed Time: 0:00:00 ETA: 0:00:00C:\Users\SCSE\AppData\Local\Continuum\miniconda3\envs\stmicro\lib\site-packages\sklearn\metrics\_classification.py:1272: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior. _warn_prf(average, modifier, msg_start, len(result))
=== Performance result === Accuracy: 42.224999999999994 (+/-) 6.415752099325535 Testing Loss: 0.7078339606523514 (+/-) 0.011477615142251374 Precision: 0.1782950625 Recall: 0.42225 F1 score: 0.25072253471611883 Testing Time: 0.001864622939716686 (+/-) 0.0008186299166247629 Training Time: 0.0 (+/-) 0.0 === Average network evolution === Total hidden node: 2.0 (+/-) 0.0 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=8, out_features=2, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=2, out_features=2, bias=True) ) No. of inputs : 8 No. of nodes : 2 No. of parameters : 24 Voting weight: [1.0]
62% (28 of 45) |############## | Elapsed Time: 0:00:00 ETA: 0:00:00
=== Performance result === Accuracy: 59.875 (+/-) 4.9883101984904314 Testing Loss: 0.6765508136966012 (+/-) 0.007964352247653643 Precision: 0.6121393426221168 Recall: 0.59875 F1 score: 0.6011688329766939 Testing Time: 0.003228967840021307 (+/-) 0.008454607571139713 Training Time: 0.0 (+/-) 0.0 === Average network evolution === Total hidden node: 5.0 (+/-) 0.0 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=8, out_features=5, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=5, out_features=2, bias=True) ) No. of inputs : 8 No. of nodes : 5 No. of parameters : 57 Voting weight: [1.0]
100% (45 of 45) |########################| Elapsed Time: 0:00:00 ETA: 00:00:00C:\Users\SCSE\AppData\Local\Continuum\miniconda3\envs\stmicro\lib\site-packages\sklearn\metrics\_classification.py:1272: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior. _warn_prf(average, modifier, msg_start, len(result))
=== Performance result === Accuracy: 57.775000000000006 (+/-) 6.415752099325535 Testing Loss: 0.6815451668067412 (+/-) 0.024320144526084716 Precision: 0.33379506249999996 Recall: 0.57775 F1 score: 0.4231279511963239 Testing Time: 0.003649592399597168 (+/-) 0.00881343691001829 Training Time: 0.0 (+/-) 0.0 === Average network evolution === Total hidden node: 5.0 (+/-) 0.0 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=8, out_features=5, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=5, out_features=2, bias=True) ) No. of inputs : 8 No. of nodes : 5 No. of parameters : 57 Voting weight: [1.0]
Mean Accuracy: 54.98 Std Accuracy: 8.96195680459585 Hidden Node mean 4.4 Hidden Node std: 1.3564659966250538 Hidden Layer mean: 1.0 Hidden Layer std: 0.0
In [2]:
%run ADL_creditcarddefault.ipynb
Number of input: 24 Number of output: 2 Number of batch: 30 All labeled
100% (30 of 30) |########################| Elapsed Time: 0:00:40 ETA: 00:00:00
=== Performance result === Accuracy: 79.3896551724138 (+/-) 2.4256310700497083 Testing Loss: 0.48540904604155444 (+/-) 0.03809364072112745 Precision: 0.776913854983997 Recall: 0.793896551724138 F1 score: 0.7315256663773451 Testing Time: 0.004904968985195817 (+/-) 0.011163449589942528 Training Time: 1.3742512670056573 (+/-) 0.12193839479107552 === Average network evolution === Total hidden node: 9.0 (+/-) 0.0 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=24, out_features=9, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=9, out_features=2, bias=True) ) No. of inputs : 24 No. of nodes : 9 No. of parameters : 245 Voting weight: [1.0]
100% (30 of 30) |########################| Elapsed Time: 0:00:40 ETA: 00:00:00
=== Performance result === Accuracy: 79.44482758620688 (+/-) 2.461648761591691 Testing Loss: 0.4819189649203728 (+/-) 0.03401801656168297 Precision: 0.7773021350088571 Recall: 0.794448275862069 F1 score: 0.7331888341141605 Testing Time: 0.004325891363209692 (+/-) 0.007647290769928797 Training Time: 1.3800063626519565 (+/-) 0.13415800508112583 === Average network evolution === Total hidden node: 7.0 (+/-) 0.0 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=24, out_features=7, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=7, out_features=2, bias=True) ) No. of inputs : 24 No. of nodes : 7 No. of parameters : 191 Voting weight: [1.0]
100% (30 of 30) |########################| Elapsed Time: 0:00:38 ETA: 00:00:00
=== Performance result === Accuracy: 79.17241379310343 (+/-) 2.3066465510636625 Testing Loss: 0.4874982916075608 (+/-) 0.035170076520138656 Precision: 0.7696894777362865 Recall: 0.7917241379310345 F1 score: 0.7286301397962517 Testing Time: 0.004690869101162614 (+/-) 0.01100127860645828 Training Time: 1.3074448026459793 (+/-) 0.09246301334111769 === Average network evolution === Total hidden node: 8.655172413793103 (+/-) 0.4753120259341456 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=24, out_features=9, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=9, out_features=2, bias=True) ) No. of inputs : 24 No. of nodes : 9 No. of parameters : 245 Voting weight: [1.0]
100% (30 of 30) |########################| Elapsed Time: 0:00:40 ETA: 00:00:00
=== Performance result === Accuracy: 79.56206896551723 (+/-) 2.733876090462473 Testing Loss: 0.48361133193147593 (+/-) 0.03706356071810435 Precision: 0.7771364450254247 Recall: 0.7956206896551724 F1 score: 0.7374570867563525 Testing Time: 0.0039767314647806105 (+/-) 0.007942167915063006 Training Time: 1.4069160592967067 (+/-) 0.09628082833015346 === Average network evolution === Total hidden node: 2.2758620689655173 (+/-) 0.44694763437295587 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=24, out_features=2, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=2, out_features=2, bias=True) ) No. of inputs : 24 No. of nodes : 2 No. of parameters : 56 Voting weight: [1.0]
100% (30 of 30) |########################| Elapsed Time: 0:00:37 ETA: 00:00:00
=== Performance result === Accuracy: 79.4793103448276 (+/-) 2.481292670661643 Testing Loss: 0.4827772820818013 (+/-) 0.035787671050558356 Precision: 0.7758179857184158 Recall: 0.7947931034482759 F1 score: 0.7354864510010255 Testing Time: 0.004394333938072468 (+/-) 0.008634893684487357 Training Time: 1.3015536028763344 (+/-) 0.05212098274112415 === Average network evolution === Total hidden node: 7.724137931034483 (+/-) 0.4469476343729559 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=24, out_features=8, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=8, out_features=2, bias=True) ) No. of inputs : 24 No. of nodes : 8 No. of parameters : 218 Voting weight: [1.0]
========== Performance creditcarddefault ========== Preq Accuracy: 79.41 (+/-) 0.13 F1 score: 0.73 (+/-) 0.0 Precision: 0.78 (+/-) 0.0 Recall: 0.79 (+/-) 0.0 Training time: 1.35 (+/-) 0.04 Testing time: 0.0 (+/-) 0.0 ========== Network ========== Number of hidden layers: 1.0 (+/-) 0.0 Number of features: 7.0 (+/-) 2.61 50% labeled
100% (30 of 30) |########################| Elapsed Time: 0:00:19 ETA: 00:00:00
=== Performance result === Accuracy: 78.89655172413794 (+/-) 2.787593543644049 Testing Loss: 0.4922558459742316 (+/-) 0.037597359582854525 Precision: 0.7753999015883385 Recall: 0.7889655172413793 F1 score: 0.7155581449072997 Testing Time: 0.00466130519735402 (+/-) 0.009320271489723789 Training Time: 0.6538175961066937 (+/-) 0.025377348704353365 === Average network evolution === Total hidden node: 10.0 (+/-) 0.0 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=24, out_features=10, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=10, out_features=2, bias=True) ) No. of inputs : 24 No. of nodes : 10 No. of parameters : 272 Voting weight: [1.0]
100% (30 of 30) |########################| Elapsed Time: 0:00:19 ETA: 00:00:00
=== Performance result === Accuracy: 78.87241379310343 (+/-) 2.7839313001487085 Testing Loss: 0.4971512031966242 (+/-) 0.03808596792324475 Precision: 0.7705951061544142 Recall: 0.7887241379310345 F1 score: 0.7167964790931977 Testing Time: 0.00424931789266652 (+/-) 0.007887688761866943 Training Time: 0.6554858520113188 (+/-) 0.027822346544190846 === Average network evolution === Total hidden node: 9.206896551724139 (+/-) 0.7601864718982275 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=24, out_features=10, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=10, out_features=2, bias=True) ) No. of inputs : 24 No. of nodes : 10 No. of parameters : 272 Voting weight: [1.0]
100% (30 of 30) |########################| Elapsed Time: 0:00:19 ETA: 00:00:00
=== Performance result === Accuracy: 78.54137931034482 (+/-) 2.2418461052382557 Testing Loss: 0.4964591110574788 (+/-) 0.03663090625051788 Precision: 0.76994416783673 Recall: 0.7854137931034483 F1 score: 0.7052768267891905 Testing Time: 0.004695341504853347 (+/-) 0.010822525236039337 Training Time: 0.6824125257031671 (+/-) 0.0456319824648727 === Average network evolution === Total hidden node: 7.344827586206897 (+/-) 0.4753120259341456 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=24, out_features=8, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=8, out_features=2, bias=True) ) No. of inputs : 24 No. of nodes : 8 No. of parameters : 218 Voting weight: [1.0]
100% (30 of 30) |########################| Elapsed Time: 0:00:20 ETA: 00:00:00
=== Performance result === Accuracy: 78.81724137931033 (+/-) 2.6206170588856046 Testing Loss: 0.49600325884490176 (+/-) 0.04323257298510106 Precision: 0.7827014310137869 Recall: 0.7881724137931034 F1 score: 0.710711283034088 Testing Time: 0.005172696606866245 (+/-) 0.01185685358429328 Training Time: 0.6977325390125143 (+/-) 0.05963958176416625 === Average network evolution === Total hidden node: 8.0 (+/-) 0.0 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=24, out_features=8, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=8, out_features=2, bias=True) ) No. of inputs : 24 No. of nodes : 8 No. of parameters : 218 Voting weight: [1.0]
100% (30 of 30) |########################| Elapsed Time: 0:00:20 ETA: 00:00:00
=== Performance result === Accuracy: 78.61724137931034 (+/-) 2.2900186666182805 Testing Loss: 0.49729508367078057 (+/-) 0.03655898527691127 Precision: 0.773085379351646 Recall: 0.7861724137931034 F1 score: 0.7069655964679372 Testing Time: 0.004796398097071154 (+/-) 0.010954202781788826 Training Time: 0.7016903778602337 (+/-) 0.04620810989139147 === Average network evolution === Total hidden node: 6.931034482758621 (+/-) 0.2533954906327425 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=24, out_features=7, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=7, out_features=2, bias=True) ) No. of inputs : 24 No. of nodes : 7 No. of parameters : 191 Voting weight: [1.0]
========== Performance creditcarddefault ========== Preq Accuracy: 78.75 (+/-) 0.14 F1 score: 0.71 (+/-) 0.0 Precision: 0.77 (+/-) 0.0 Recall: 0.79 (+/-) 0.0 Training time: 0.68 (+/-) 0.02 Testing time: 0.0 (+/-) 0.0 ========== Network ========== Number of hidden layers: 1.0 (+/-) 0.0 Number of features: 8.6 (+/-) 1.2 25% labeled
100% (30 of 30) |########################| Elapsed Time: 0:00:10 ETA: 00:00:00
=== Performance result === Accuracy: 78.2551724137931 (+/-) 2.6147573510282447 Testing Loss: 0.5008028046838169 (+/-) 0.03829689810008438 Precision: 0.7725041006081595 Recall: 0.7825517241379311 F1 score: 0.6949309475030001 Testing Time: 0.004353432819761079 (+/-) 0.0071086261519850156 Training Time: 0.3419438970500025 (+/-) 0.014907215794696001 === Average network evolution === Total hidden node: 9.862068965517242 (+/-) 0.3448275862068966 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=24, out_features=10, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=10, out_features=2, bias=True) ) No. of inputs : 24 No. of nodes : 10 No. of parameters : 272 Voting weight: [1.0]
100% (30 of 30) |########################| Elapsed Time: 0:00:11 ETA: 00:00:00
=== Performance result === Accuracy: 78.12758620689657 (+/-) 2.505978582582357 Testing Loss: 0.5080117203038315 (+/-) 0.038214718247245275 Precision: 0.7777589311933805 Recall: 0.7812758620689655 F1 score: 0.6902127758442113 Testing Time: 0.004114192107628132 (+/-) 0.007372065537259306 Training Time: 0.385124790257421 (+/-) 0.04847479697013953 === Average network evolution === Total hidden node: 6.9655172413793105 (+/-) 0.18246560765962697 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=24, out_features=7, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=7, out_features=2, bias=True) ) No. of inputs : 24 No. of nodes : 7 No. of parameters : 191 Voting weight: [1.0]
100% (30 of 30) |########################| Elapsed Time: 0:00:09 ETA: 00:00:00
=== Performance result === Accuracy: 78.33793103448275 (+/-) 2.636666363513809 Testing Loss: 0.5031268781629102 (+/-) 0.03410298416811261 Precision: 0.7720549229497322 Recall: 0.7833793103448276 F1 score: 0.6977832925987967 Testing Time: 0.004520901318254142 (+/-) 0.009529105061820926 Training Time: 0.3387431605108853 (+/-) 0.014098297091703479 === Average network evolution === Total hidden node: 9.0 (+/-) 0.0 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=24, out_features=9, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=9, out_features=2, bias=True) ) No. of inputs : 24 No. of nodes : 9 No. of parameters : 245 Voting weight: [1.0]
100% (30 of 30) |########################| Elapsed Time: 0:00:10 ETA: 00:00:00
=== Performance result === Accuracy: 78.02413793103449 (+/-) 2.515970392404844 Testing Loss: 0.5111399991758938 (+/-) 0.03815259725378138 Precision: 0.7655688100903677 Recall: 0.7802413793103449 F1 score: 0.6876942559342658 Testing Time: 0.004995428282639076 (+/-) 0.009644079968857688 Training Time: 0.3644144946131213 (+/-) 0.026812147179565187 === Average network evolution === Total hidden node: 9.689655172413794 (+/-) 0.46263475396547366 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=24, out_features=10, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=10, out_features=2, bias=True) ) No. of inputs : 24 No. of nodes : 10 No. of parameters : 272 Voting weight: [1.0]
100% (30 of 30) |########################| Elapsed Time: 0:00:10 ETA: 00:00:00
=== Performance result === Accuracy: 78.16896551724139 (+/-) 2.486807044117619 Testing Loss: 0.5055427551269531 (+/-) 0.03750729511547445 Precision: 0.7739529376834158 Recall: 0.7816896551724138 F1 score: 0.6918942605953049 Testing Time: 0.004529344624486463 (+/-) 0.008230167129608657 Training Time: 0.3597124773880531 (+/-) 0.029691113728100817 === Average network evolution === Total hidden node: 8.89655172413793 (+/-) 0.30454347814923605 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=24, out_features=9, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=9, out_features=2, bias=True) ) No. of inputs : 24 No. of nodes : 9 No. of parameters : 245 Voting weight: [1.0]
========== Performance creditcarddefault ========== Preq Accuracy: 78.18 (+/-) 0.11 F1 score: 0.69 (+/-) 0.0 Precision: 0.77 (+/-) 0.0 Recall: 0.78 (+/-) 0.0 Training time: 0.36 (+/-) 0.02 Testing time: 0.0 (+/-) 0.0 ========== Network ========== Number of hidden layers: 1.0 (+/-) 0.0 Number of features: 9.0 (+/-) 1.1 Infinite Delay
100% (30 of 30) |########################| Elapsed Time: 0:00:00 ETA: 00:00:00C:\Users\SCSE\AppData\Local\Continuum\miniconda3\envs\stmicro\lib\site-packages\sklearn\metrics\_classification.py:1221: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior. _warn_prf(average, modifier, msg_start, len(result))
=== Performance result === Accuracy: 77.85517241379311 (+/-) 2.505247762115322 Testing Loss: 0.5179515604315132 (+/-) 0.029585884799812553 Precision: 0.6061427871581452 Recall: 0.7785517241379311 F1 score: 0.6816138984678044 Testing Time: 0.0038176980511895543 (+/-) 0.009293943318511539 Training Time: 0.0 (+/-) 0.0 === Average network evolution === Total hidden node: 9.0 (+/-) 0.0 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=24, out_features=9, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=9, out_features=2, bias=True) ) No. of inputs : 24 No. of nodes : 9 No. of parameters : 245 Voting weight: [1.0]
23% (7 of 30) |##### | Elapsed Time: 0:00:00 ETA: 00:00:00C:\Users\SCSE\AppData\Local\Continuum\miniconda3\envs\stmicro\lib\site-packages\sklearn\metrics\_classification.py:1221: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior. _warn_prf(average, modifier, msg_start, len(result))
=== Performance result === Accuracy: 77.85517241379311 (+/-) 2.505247762115322 Testing Loss: 0.5303484386411207 (+/-) 0.024345815101068986 Precision: 0.6061427871581452 Recall: 0.7785517241379311 F1 score: 0.6816138984678044 Testing Time: 0.0030955692817424907 (+/-) 0.00774706523748648 Training Time: 0.0 (+/-) 0.0 === Average network evolution === Total hidden node: 12.0 (+/-) 0.0 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=24, out_features=12, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=12, out_features=2, bias=True) ) No. of inputs : 24 No. of nodes : 12 No. of parameters : 326 Voting weight: [1.0]
90% (27 of 30) |##################### | Elapsed Time: 0:00:00 ETA: 0:00:00C:\Users\SCSE\AppData\Local\Continuum\miniconda3\envs\stmicro\lib\site-packages\sklearn\metrics\_classification.py:1221: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior. _warn_prf(average, modifier, msg_start, len(result))
=== Performance result === Accuracy: 77.85517241379311 (+/-) 2.505247762115322 Testing Loss: 0.5301857868145252 (+/-) 0.03649751731048925 Precision: 0.6061427871581452 Recall: 0.7785517241379311 F1 score: 0.6816138984678044 Testing Time: 0.003736841267552869 (+/-) 0.009134597385075535 Training Time: 0.0 (+/-) 0.0 === Average network evolution === Total hidden node: 9.0 (+/-) 0.0 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=24, out_features=9, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=9, out_features=2, bias=True) ) No. of inputs : 24 No. of nodes : 9 No. of parameters : 245 Voting weight: [1.0]
100% (30 of 30) |########################| Elapsed Time: 0:00:00 ETA: 00:00:00C:\Users\SCSE\AppData\Local\Continuum\miniconda3\envs\stmicro\lib\site-packages\sklearn\metrics\_classification.py:1221: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior. _warn_prf(average, modifier, msg_start, len(result))
=== Performance result === Accuracy: 77.85517241379311 (+/-) 2.505247762115322 Testing Loss: 0.5242518535975752 (+/-) 0.027918092537379036 Precision: 0.6061427871581452 Recall: 0.7785517241379311 F1 score: 0.6816138984678044 Testing Time: 0.0035066686827560953 (+/-) 0.007303613424009609 Training Time: 0.0 (+/-) 0.0 === Average network evolution === Total hidden node: 10.0 (+/-) 0.0 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=24, out_features=10, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=10, out_features=2, bias=True) ) No. of inputs : 24 No. of nodes : 10 No. of parameters : 272 Voting weight: [1.0]
93% (28 of 30) |###################### | Elapsed Time: 0:00:00 ETA: 0:00:00
=== Performance result === Accuracy: 77.85172413793104 (+/-) 2.4994648654372584 Testing Loss: 0.5475063776147777 (+/-) 0.02134287169415684 Precision: 0.694746069179585 Recall: 0.7785172413793103 F1 score: 0.6817272279677457 Testing Time: 0.004071350755362675 (+/-) 0.009477252269679532 Training Time: 0.0 (+/-) 0.0 === Average network evolution === Total hidden node: 8.0 (+/-) 0.0 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=24, out_features=8, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=8, out_features=2, bias=True) ) No. of inputs : 24 No. of nodes : 8 No. of parameters : 218 Voting weight: [1.0]
========== Performance creditcarddefault ========== Preq Accuracy: 77.85 (+/-) 0.0 F1 score: 0.68 (+/-) 0.0 Precision: 0.62 (+/-) 0.04 Recall: 0.78 (+/-) 0.0 Training time: 0.0 (+/-) 0.0 Testing time: 0.0 (+/-) 0.0 ========== Network ========== Number of hidden layers: 1.0 (+/-) 0.0 Number of features: 9.6 (+/-) 1.36
In [1]:
%run ADL_occupancy.ipynb
Number of input: 5 Number of output: 2 Number of batch: 20 All labeled
100% (20 of 20) |########################| Elapsed Time: 0:00:46 ETA: 00:00:00
=== Performance result === Accuracy: 79.36315789473684 (+/-) 21.316591277967298 Testing Loss: 0.6024326111288055 (+/-) 0.5022846505432366 Precision: 0.8035568230062642 Recall: 0.7936315789473685 F1 score: 0.728141900913471 Testing Time: 0.01353714340611508 (+/-) 0.01505660850428367 Training Time: 2.4085363588835063 (+/-) 1.0346452528844443 === Average network evolution === Total hidden node: 40.05263157894737 (+/-) 22.108521063180774 Number of layer: 5.2105263157894735 (+/-) 2.5869906794620015 === Final network structure === basicNet( (linear): Linear(in_features=5, out_features=7, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=7, out_features=2, bias=True) ) No. of inputs : 5 No. of nodes : 7 No. of parameters : 58 basicNet( (linear): Linear(in_features=7, out_features=15, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=15, out_features=2, bias=True) ) No. of inputs : 7 No. of nodes : 15 No. of parameters : 152 basicNet( (linear): Linear(in_features=15, out_features=8, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=8, out_features=2, bias=True) ) No. of inputs : 15 No. of nodes : 8 No. of parameters : 146 basicNet( (linear): Linear(in_features=8, out_features=6, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=6, out_features=2, bias=True) ) No. of inputs : 8 No. of nodes : 6 No. of parameters : 68 basicNet( (linear): Linear(in_features=6, out_features=7, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=7, out_features=2, bias=True) ) No. of inputs : 6 No. of nodes : 7 No. of parameters : 65 basicNet( (linear): Linear(in_features=7, out_features=7, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=7, out_features=2, bias=True) ) No. of inputs : 7 No. of nodes : 7 No. of parameters : 72 basicNet( (linear): Linear(in_features=7, out_features=13, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=13, out_features=2, bias=True) ) No. of inputs : 7 No. of nodes : 13 No. of parameters : 132 basicNet( (linear): Linear(in_features=13, out_features=4, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=4, out_features=2, bias=True) ) No. of inputs : 13 No. of nodes : 4 No. of parameters : 66 Voting weight: [0.0, 0.5, 0.0, 0.0, 0.0, 0.0, 0.0, 0.5]
100% (20 of 20) |########################| Elapsed Time: 0:00:41 ETA: 00:00:00
=== Performance result === Accuracy: 78.89473684210527 (+/-) 21.620201899933907 Testing Loss: 0.5778865523293222 (+/-) 0.5102719055627148 Precision: 0.7636236479942705 Recall: 0.7889473684210526 F1 score: 0.7382051995586141 Testing Time: 0.012738591746280068 (+/-) 0.01581409295519164 Training Time: 2.1933474666193913 (+/-) 0.7422607283012801 === Average network evolution === Total hidden node: 42.421052631578945 (+/-) 19.279975402565892 Number of layer: 4.526315789473684 (+/-) 2.209272827559511 === Final network structure === basicNet( (linear): Linear(in_features=5, out_features=15, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=15, out_features=2, bias=True) ) No. of inputs : 5 No. of nodes : 15 No. of parameters : 122 basicNet( (linear): Linear(in_features=15, out_features=26, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=26, out_features=2, bias=True) ) No. of inputs : 15 No. of nodes : 26 No. of parameters : 470 basicNet( (linear): Linear(in_features=26, out_features=7, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=7, out_features=2, bias=True) ) No. of inputs : 26 No. of nodes : 7 No. of parameters : 205 basicNet( (linear): Linear(in_features=7, out_features=4, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=4, out_features=2, bias=True) ) No. of inputs : 7 No. of nodes : 4 No. of parameters : 42 basicNet( (linear): Linear(in_features=4, out_features=6, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=6, out_features=2, bias=True) ) No. of inputs : 4 No. of nodes : 6 No. of parameters : 44 basicNet( (linear): Linear(in_features=6, out_features=11, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=11, out_features=2, bias=True) ) No. of inputs : 6 No. of nodes : 11 No. of parameters : 101 basicNet( (linear): Linear(in_features=11, out_features=3, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=3, out_features=2, bias=True) ) No. of inputs : 11 No. of nodes : 3 No. of parameters : 44 Voting weight: [0.0, 0.5, 0.0, 0.0, 0.0, 0.0, 0.5]
100% (20 of 20) |########################| Elapsed Time: 0:00:56 ETA: 00:00:00
=== Performance result === Accuracy: 73.94210526315791 (+/-) 23.725986547942114 Testing Loss: 0.6573177707920733 (+/-) 0.532981730478131 Precision: 0.6431281002838621 Recall: 0.739421052631579 F1 score: 0.6730843058959716 Testing Time: 0.014475596578497636 (+/-) 0.01729962848367366 Training Time: 2.9618207906421863 (+/-) 1.566768067577372 === Average network evolution === Total hidden node: 47.31578947368421 (+/-) 26.828995766715074 Number of layer: 5.368421052631579 (+/-) 2.7949301152319483 === Final network structure === basicNet( (linear): Linear(in_features=5, out_features=9, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=9, out_features=2, bias=True) ) No. of inputs : 5 No. of nodes : 9 No. of parameters : 74 basicNet( (linear): Linear(in_features=9, out_features=13, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=13, out_features=2, bias=True) ) No. of inputs : 9 No. of nodes : 13 No. of parameters : 158 basicNet( (linear): Linear(in_features=13, out_features=6, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=6, out_features=2, bias=True) ) No. of inputs : 13 No. of nodes : 6 No. of parameters : 98 basicNet( (linear): Linear(in_features=6, out_features=8, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=8, out_features=2, bias=True) ) No. of inputs : 6 No. of nodes : 8 No. of parameters : 74 basicNet( (linear): Linear(in_features=8, out_features=5, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=5, out_features=2, bias=True) ) No. of inputs : 8 No. of nodes : 5 No. of parameters : 57 basicNet( (linear): Linear(in_features=5, out_features=6, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=6, out_features=2, bias=True) ) No. of inputs : 5 No. of nodes : 6 No. of parameters : 50 basicNet( (linear): Linear(in_features=6, out_features=22, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=22, out_features=2, bias=True) ) No. of inputs : 6 No. of nodes : 22 No. of parameters : 200 basicNet( (linear): Linear(in_features=22, out_features=6, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=6, out_features=2, bias=True) ) No. of inputs : 22 No. of nodes : 6 No. of parameters : 152 basicNet( (linear): Linear(in_features=6, out_features=5, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=5, out_features=2, bias=True) ) No. of inputs : 6 No. of nodes : 5 No. of parameters : 47 basicNet( (linear): Linear(in_features=5, out_features=7, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=7, out_features=2, bias=True) ) No. of inputs : 5 No. of nodes : 7 No. of parameters : 58 Voting weight: [0.0, 0.00024987506246876566, 0.0, 0.0, 0.0, 0.0, 0.0, 0.24987506246876562, 0.24987506246876562, 0.5]
100% (20 of 20) |########################| Elapsed Time: 0:00:49 ETA: 00:00:00
=== Performance result === Accuracy: 79.89473684210526 (+/-) 21.352344224419866 Testing Loss: 0.5781744434253165 (+/-) 0.5112402806704262 Precision: 0.8003892825935593 Recall: 0.7989473684210526 F1 score: 0.7425371639881438 Testing Time: 0.012168357246800474 (+/-) 0.015717456890684874 Training Time: 2.591645692524157 (+/-) 0.912847894321539 === Average network evolution === Total hidden node: 39.89473684210526 (+/-) 19.341514491515 Number of layer: 4.526315789473684 (+/-) 2.209272827559511 === Final network structure === basicNet( (linear): Linear(in_features=5, out_features=12, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=12, out_features=2, bias=True) ) No. of inputs : 5 No. of nodes : 12 No. of parameters : 98 basicNet( (linear): Linear(in_features=12, out_features=16, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=16, out_features=2, bias=True) ) No. of inputs : 12 No. of nodes : 16 No. of parameters : 242 basicNet( (linear): Linear(in_features=16, out_features=8, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=8, out_features=2, bias=True) ) No. of inputs : 16 No. of nodes : 8 No. of parameters : 154 basicNet( (linear): Linear(in_features=8, out_features=6, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=6, out_features=2, bias=True) ) No. of inputs : 8 No. of nodes : 6 No. of parameters : 68 basicNet( (linear): Linear(in_features=6, out_features=7, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=7, out_features=2, bias=True) ) No. of inputs : 6 No. of nodes : 7 No. of parameters : 65 basicNet( (linear): Linear(in_features=7, out_features=13, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=13, out_features=2, bias=True) ) No. of inputs : 7 No. of nodes : 13 No. of parameters : 132 basicNet( (linear): Linear(in_features=13, out_features=3, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=3, out_features=2, bias=True) ) No. of inputs : 13 No. of nodes : 3 No. of parameters : 50 Voting weight: [0.0, 0.5, 0.0, 0.0, 0.0, 0.0, 0.5]
100% (20 of 20) |########################| Elapsed Time: 0:00:50 ETA: 00:00:00
=== Performance result === Accuracy: 78.4421052631579 (+/-) 21.10822528104235 Testing Loss: 0.6779582000668406 (+/-) 0.7989469552912296 Precision: 0.7526346186977521 Recall: 0.7844210526315789 F1 score: 0.7349475452717785 Testing Time: 0.012276160089593185 (+/-) 0.014050232114699255 Training Time: 2.6550418075762297 (+/-) 1.125776950129026 === Average network evolution === Total hidden node: 38.73684210526316 (+/-) 19.841058188204098 Number of layer: 4.578947368421052 (+/-) 2.2784064023066697 === Final network structure === basicNet( (linear): Linear(in_features=5, out_features=9, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=9, out_features=2, bias=True) ) No. of inputs : 5 No. of nodes : 9 No. of parameters : 74 basicNet( (linear): Linear(in_features=9, out_features=16, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=16, out_features=2, bias=True) ) No. of inputs : 9 No. of nodes : 16 No. of parameters : 194 basicNet( (linear): Linear(in_features=16, out_features=8, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=8, out_features=2, bias=True) ) No. of inputs : 16 No. of nodes : 8 No. of parameters : 154 basicNet( (linear): Linear(in_features=8, out_features=2, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=2, out_features=2, bias=True) ) No. of inputs : 8 No. of nodes : 2 No. of parameters : 24 basicNet( (linear): Linear(in_features=2, out_features=10, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=10, out_features=2, bias=True) ) No. of inputs : 2 No. of nodes : 10 No. of parameters : 52 basicNet( (linear): Linear(in_features=10, out_features=10, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=10, out_features=2, bias=True) ) No. of inputs : 10 No. of nodes : 10 No. of parameters : 132 basicNet( (linear): Linear(in_features=10, out_features=6, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=6, out_features=2, bias=True) ) No. of inputs : 10 No. of nodes : 6 No. of parameters : 80 basicNet( (linear): Linear(in_features=6, out_features=6, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=6, out_features=2, bias=True) ) No. of inputs : 6 No. of nodes : 6 No. of parameters : 56 Voting weight: [0.0, 0.4995004995004996, 0.0, 0.0, 0.0, 0.0, 0.0004995004995004996, 0.5]
========== Performance creditcarddefault ========== Preq Accuracy: 78.11 (+/-) 2.14 F1 score: 0.72 (+/-) 0.03 Precision: 0.75 (+/-) 0.06 Recall: 0.78 (+/-) 0.02 Training time: 2.56 (+/-) 0.26 Testing time: 0.01 (+/-) 0.0 ========== Network ========== Number of hidden layers: 8.0 (+/-) 1.1 Number of features: 71.6 (+/-) 8.04 50% labeled
100% (20 of 20) |########################| Elapsed Time: 0:00:13 ETA: 00:00:00
=== Performance result === Accuracy: 78.1421052631579 (+/-) 26.163098074024507 Testing Loss: 0.45945386696410806 (+/-) 0.43151298380472075 Precision: 0.7656969211889554 Recall: 0.7814210526315789 F1 score: 0.7711544838693642 Testing Time: 0.005294849998072574 (+/-) 0.01006458088742868 Training Time: 0.7207258249583998 (+/-) 0.0711004179549971 === Average network evolution === Total hidden node: 7.894736842105263 (+/-) 1.943808980275725 Number of layer: 1.105263157894737 (+/-) 0.30689220499185793 === Final network structure === basicNet( (linear): Linear(in_features=5, out_features=13, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=13, out_features=2, bias=True) ) No. of inputs : 5 No. of nodes : 13 No. of parameters : 106 Voting weight: [1.0]
100% (20 of 20) |########################| Elapsed Time: 0:00:13 ETA: 00:00:00
=== Performance result === Accuracy: 82.67894736842105 (+/-) 17.99864260809887 Testing Loss: 0.4395388616739135 (+/-) 0.45794847045749076 Precision: 0.8138033565236272 Recall: 0.8267894736842105 F1 score: 0.8134807373935803 Testing Time: 0.005715319984837582 (+/-) 0.01279211371586753 Training Time: 0.6962569889269377 (+/-) 0.04369946785831234 === Average network evolution === Total hidden node: 7.947368421052632 (+/-) 2.416471638578736 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=5, out_features=14, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=14, out_features=2, bias=True) ) No. of inputs : 5 No. of nodes : 14 No. of parameters : 114 Voting weight: [1.0]
100% (20 of 20) |########################| Elapsed Time: 0:00:13 ETA: 00:00:00
=== Performance result === Accuracy: 78.67368421052633 (+/-) 23.564086012075403 Testing Loss: 0.44651137743341296 (+/-) 0.4425940797623028 Precision: 0.7712179492723577 Recall: 0.7867368421052632 F1 score: 0.7763664628718513 Testing Time: 0.006992603603162263 (+/-) 0.01235976050741714 Training Time: 0.6854561881015175 (+/-) 0.030143744446296146 === Average network evolution === Total hidden node: 14.631578947368421 (+/-) 3.989598664894153 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=5, out_features=22, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=22, out_features=2, bias=True) ) No. of inputs : 5 No. of nodes : 22 No. of parameters : 178 Voting weight: [1.0]
100% (20 of 20) |########################| Elapsed Time: 0:00:12 ETA: 00:00:00
=== Performance result === Accuracy: 82.93684210526317 (+/-) 18.144078649181964 Testing Loss: 0.4381990016585118 (+/-) 0.4426637922722925 Precision: 0.8168599814194805 Recall: 0.8293684210526315 F1 score: 0.815852950708329 Testing Time: 0.004508620814273232 (+/-) 0.008365441937548972 Training Time: 0.6772381380984658 (+/-) 0.05873748399571789 === Average network evolution === Total hidden node: 9.736842105263158 (+/-) 2.8808278280850543 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=5, out_features=17, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=17, out_features=2, bias=True) ) No. of inputs : 5 No. of nodes : 17 No. of parameters : 138 Voting weight: [1.0]
100% (20 of 20) |########################| Elapsed Time: 0:00:18 ETA: 00:00:00
=== Performance result === Accuracy: 73.34210526315789 (+/-) 27.46770957419052 Testing Loss: 0.6483429189477312 (+/-) 0.6793301750054619 Precision: 0.6824332837150368 Recall: 0.733421052631579 F1 score: 0.6985089109428686 Testing Time: 0.005968545612535979 (+/-) 0.010855997621176082 Training Time: 0.9414331034610146 (+/-) 0.09611270242832352 === Average network evolution === Total hidden node: 18.210526315789473 (+/-) 6.970456055218233 Number of layer: 1.894736842105263 (+/-) 0.30689220499185793 === Final network structure === basicNet( (linear): Linear(in_features=5, out_features=5, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=5, out_features=2, bias=True) ) No. of inputs : 5 No. of nodes : 5 No. of parameters : 42 basicNet( (linear): Linear(in_features=5, out_features=19, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=19, out_features=2, bias=True) ) No. of inputs : 5 No. of nodes : 19 No. of parameters : 154 Voting weight: [0.0, 1.0]
========== Performance creditcarddefault ========== Preq Accuracy: 79.15 (+/-) 3.51 F1 score: 0.78 (+/-) 0.04 Precision: 0.77 (+/-) 0.05 Recall: 0.79 (+/-) 0.04 Training time: 0.74 (+/-) 0.1 Testing time: 0.01 (+/-) 0.0 ========== Network ========== Number of hidden layers: 1.2 (+/-) 0.4 Number of features: 18.0 (+/-) 4.34 25% labeled
100% (20 of 20) |########################| Elapsed Time: 0:00:09 ETA: 00:00:00
=== Performance result === Accuracy: 66.11578947368422 (+/-) 30.047370725816027 Testing Loss: 0.7605385647988633 (+/-) 0.6250741495770932 Precision: 0.6181622192982457 Recall: 0.6611578947368421 F1 score: 0.6374759268636577 Testing Time: 0.005909706416882966 (+/-) 0.01038528239880387 Training Time: 0.4916011032305266 (+/-) 0.06351961425483492 === Average network evolution === Total hidden node: 17.57894736842105 (+/-) 4.568954613518043 Number of layer: 1.894736842105263 (+/-) 0.30689220499185793 === Final network structure === basicNet( (linear): Linear(in_features=5, out_features=7, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=7, out_features=2, bias=True) ) No. of inputs : 5 No. of nodes : 7 No. of parameters : 58 basicNet( (linear): Linear(in_features=7, out_features=14, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=14, out_features=2, bias=True) ) No. of inputs : 7 No. of nodes : 14 No. of parameters : 142 Voting weight: [0.0, 1.0]
100% (20 of 20) |########################| Elapsed Time: 0:00:07 ETA: 00:00:00
=== Performance result === Accuracy: 80.6263157894737 (+/-) 20.356063162586825 Testing Loss: 0.4822707970773703 (+/-) 0.4385902946140286 Precision: 0.788320890454088 Recall: 0.8062631578947368 F1 score: 0.7741719818993091 Testing Time: 0.002770072535464638 (+/-) 0.0008352738109608479 Training Time: 0.36644915530556127 (+/-) 0.02659829970930831 === Average network evolution === Total hidden node: 7.894736842105263 (+/-) 1.9165412058982236 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=5, out_features=11, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=11, out_features=2, bias=True) ) No. of inputs : 5 No. of nodes : 11 No. of parameters : 90 Voting weight: [1.0]
100% (20 of 20) |########################| Elapsed Time: 0:00:09 ETA: 00:00:00
=== Performance result === Accuracy: 68.36315789473684 (+/-) 27.864148074585692 Testing Loss: 0.7343697099162168 (+/-) 0.6245150931118894 Precision: 0.6288311990065972 Recall: 0.6836315789473684 F1 score: 0.6520506209915179 Testing Time: 0.003883537493254009 (+/-) 0.0012759864135536202 Training Time: 0.510084026738217 (+/-) 0.06135213907352488 === Average network evolution === Total hidden node: 15.842105263157896 (+/-) 5.470140553324951 Number of layer: 1.894736842105263 (+/-) 0.30689220499185793 === Final network structure === basicNet( (linear): Linear(in_features=5, out_features=5, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=5, out_features=2, bias=True) ) No. of inputs : 5 No. of nodes : 5 No. of parameters : 42 basicNet( (linear): Linear(in_features=5, out_features=15, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=15, out_features=2, bias=True) ) No. of inputs : 5 No. of nodes : 15 No. of parameters : 122 Voting weight: [0.0, 1.0]
100% (20 of 20) |########################| Elapsed Time: 0:00:06 ETA: 00:00:00
=== Performance result === Accuracy: 82.19473684210527 (+/-) 17.911991681088384 Testing Loss: 0.460278516096112 (+/-) 0.43245332072121745 Precision: 0.8075768372734144 Recall: 0.8219473684210526 F1 score: 0.8030812940670305 Testing Time: 0.002820479242425216 (+/-) 0.0008748570909540544 Training Time: 0.3392742182079114 (+/-) 0.012697157016403133 === Average network evolution === Total hidden node: 11.473684210526315 (+/-) 2.256415906339581 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=5, out_features=15, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=15, out_features=2, bias=True) ) No. of inputs : 5 No. of nodes : 15 No. of parameters : 122 Voting weight: [1.0]
100% (20 of 20) |########################| Elapsed Time: 0:00:07 ETA: 00:00:00
=== Performance result === Accuracy: 77.41052631578947 (+/-) 25.941734201999726 Testing Loss: 0.5181272623962477 (+/-) 0.48915130051920314 Precision: 0.740461229242546 Recall: 0.7741052631578947 F1 score: 0.7443048571271755 Testing Time: 0.004615997013292815 (+/-) 0.009733749383513785 Training Time: 0.3689627898366828 (+/-) 0.028713605933634184 === Average network evolution === Total hidden node: 9.894736842105264 (+/-) 1.9165412058982234 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=5, out_features=13, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=13, out_features=2, bias=True) ) No. of inputs : 5 No. of nodes : 13 No. of parameters : 106 Voting weight: [1.0]
========== Performance creditcarddefault ========== Preq Accuracy: 74.94 (+/-) 6.51 F1 score: 0.72 (+/-) 0.07 Precision: 0.72 (+/-) 0.08 Recall: 0.75 (+/-) 0.07 Training time: 0.42 (+/-) 0.07 Testing time: 0.0 (+/-) 0.0 ========== Network ========== Number of hidden layers: 1.4 (+/-) 0.49 Number of features: 16.0 (+/-) 3.9 Infinite Delay
60% (12 of 20) |############## | Elapsed Time: 0:00:00 ETA: 00:00:00
=== Performance result === Accuracy: 78.1421052631579 (+/-) 21.1080008724423 Testing Loss: 0.4289956069306323 (+/-) 0.2434010519792057 Precision: 0.8285868310896237 Recall: 0.7814210526315789 F1 score: 0.6953446881554156 Testing Time: 0.005408851723921926 (+/-) 0.010509669398954475 Training Time: 0.0 (+/-) 0.0 === Average network evolution === Total hidden node: 12.0 (+/-) 0.0 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=5, out_features=12, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=12, out_features=2, bias=True) ) No. of inputs : 5 No. of nodes : 12 No. of parameters : 98 Voting weight: [1.0]
95% (19 of 20) |###################### | Elapsed Time: 0:00:00 ETA: 0:00:00C:\Users\SCSE\AppData\Local\Continuum\miniconda3\envs\stmicro\lib\site-packages\sklearn\metrics\_classification.py:1221: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior. _warn_prf(average, modifier, msg_start, len(result))
=== Performance result === Accuracy: 77.09473684210526 (+/-) 20.698753425068876 Testing Loss: 0.5789694339036942 (+/-) 0.39321772528308785 Precision: 0.5943598448753463 Recall: 0.7709473684210526 F1 score: 0.6712337763095327 Testing Time: 0.005353262549952457 (+/-) 0.012160015263440281 Training Time: 0.0 (+/-) 0.0 === Average network evolution === Total hidden node: 7.0 (+/-) 0.0 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=5, out_features=7, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=7, out_features=2, bias=True) ) No. of inputs : 5 No. of nodes : 7 No. of parameters : 58 Voting weight: [1.0]
100% (20 of 20) |########################| Elapsed Time: 0:00:00 ETA: 00:00:00C:\Users\SCSE\AppData\Local\Continuum\miniconda3\envs\stmicro\lib\site-packages\sklearn\metrics\_classification.py:1221: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior. _warn_prf(average, modifier, msg_start, len(result))
=== Performance result === Accuracy: 77.09473684210526 (+/-) 20.698753425068876 Testing Loss: 0.5018552024113504 (+/-) 0.30412484585440563 Precision: 0.5943598448753463 Recall: 0.7709473684210526 F1 score: 0.6712337763095327 Testing Time: 0.0023089961001747533 (+/-) 0.0005569508889111216 Training Time: 0.0 (+/-) 0.0 === Average network evolution === Total hidden node: 6.0 (+/-) 0.0 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=5, out_features=6, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=6, out_features=2, bias=True) ) No. of inputs : 5 No. of nodes : 6 No. of parameters : 50 Voting weight: [1.0]
N/A% (0 of 20) | | Elapsed Time: 0:00:00 ETA: --:--:--C:\Users\SCSE\AppData\Local\Continuum\miniconda3\envs\stmicro\lib\site-packages\sklearn\metrics\_classification.py:1221: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior. _warn_prf(average, modifier, msg_start, len(result))
=== Performance result === Accuracy: 77.09473684210526 (+/-) 20.698753425068876 Testing Loss: 0.4326793473017843 (+/-) 0.21799056105542558 Precision: 0.5943598448753463 Recall: 0.7709473684210526 F1 score: 0.6712337763095327 Testing Time: 0.0021286763642963612 (+/-) 0.0007573048259582421 Training Time: 0.0 (+/-) 0.0 === Average network evolution === Total hidden node: 12.0 (+/-) 0.0 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=5, out_features=12, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=12, out_features=2, bias=True) ) No. of inputs : 5 No. of nodes : 12 No. of parameters : 98 Voting weight: [1.0]
20% (4 of 20) |##### | Elapsed Time: 0:00:00 ETA: 00:00:00C:\Users\SCSE\AppData\Local\Continuum\miniconda3\envs\stmicro\lib\site-packages\sklearn\metrics\_classification.py:1221: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior. _warn_prf(average, modifier, msg_start, len(result))
=== Performance result === Accuracy: 77.09473684210526 (+/-) 20.698753425068876 Testing Loss: 0.49313173247011083 (+/-) 0.25128548395747924 Precision: 0.5943598448753463 Recall: 0.7709473684210526 F1 score: 0.6712337763095327 Testing Time: 0.003833193528024774 (+/-) 0.009456542295028791 Training Time: 0.0 (+/-) 0.0 === Average network evolution === Total hidden node: 7.0 (+/-) 0.0 Number of layer: 1.0 (+/-) 0.0 === Final network structure === basicNet( (linear): Linear(in_features=5, out_features=7, bias=True) (activation): Sigmoid() (linearOutput): Linear(in_features=7, out_features=2, bias=True) ) No. of inputs : 5 No. of nodes : 7 No. of parameters : 58 Voting weight: [1.0]
========== Performance creditcarddefault ========== Preq Accuracy: 77.3 (+/-) 0.42 F1 score: 0.68 (+/-) 0.01 Precision: 0.64 (+/-) 0.09 Recall: 0.77 (+/-) 0.0 Training time: 0.0 (+/-) 0.0 Testing time: 0.0 (+/-) 0.0 ========== Network ========== Number of hidden layers: 1.0 (+/-) 0.0 Number of features: 8.8 (+/-) 2.64
In [ ]: